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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 25-LLAMASCOPE-RES-32K
    11. 23182
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "the" in various contexts

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

    the word "the" when it appears before a proper noun, title, or specific name (like "the Year", "the Week", "the Upper West Side", "the Month", "the Southwest", "the Heath").

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

    the definite article in the common “of the” construction, i.e., “the” immediately following “of” in phrases.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adian
    -0.17
    iest
    -0.16
    >tag
    -0.15
    sworth
    -0.14
    isco
    -0.14
    antine
    -0.14
    ront
    -0.14
    errat
    -0.14
    iko
    -0.14
    liest
    -0.13
    POSITIVE LOGITS
     senses
    0.18
     ages
    0.18
     Ages
    0.17
     apocalypse
    0.17
     Rockies
    0.17
     imagination
    0.16
    ivery
    0.16
     Month
    0.16
     Cloth
    0.16
    ENCIL
    0.15
    Activations Density 0.117%

    No Known Activations