© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-32K
    6. 15929
    Prev
    Next
    INDEX
    Explanations

    instances of the word "the" and its various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Looking at the activations, this neuron activates on the word "the" when it appears before nouns that represent organizations, institutions, programs, or specific named entities (like "the Buxton Newtown office", "the College", "the program", "the business", "

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    the definite article preceding nouns or noun phrases.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     last
    -0.17
    -animate
    -0.15
    اÙĨات
    -0.15
    ãĥ¬ãĥĥãĥĪ
    -0.14
    blade
    -0.14
    bel
    -0.14
    aman
    -0.14
     problem
    -0.14
    asan
    -0.13
    noon
    -0.13
    POSITIVE LOGITS
    TI
    0.16
    pace
    0.16
     Verd
    0.15
    olson
    0.15
     áº
    0.15
    ¾ç¤º
    0.14
    주ìĿĺ
    0.14
    eping
    0.14
    prite
    0.14
     baiser
    0.13
    Activations Density 0.199%

    No Known Activations