© 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. 11657
    Prev
    Next
    INDEX
    Explanations

    instances of the pronoun "it" and variations thereof

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

    the word "It" at the beginning of sentences in formal or technical writing.

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

    sentence-initial “It” used as a dummy/impersonal subject in statements (e.g., “It is/does …”).

    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
    onas
    -0.16
    rud
    -0.14
    -0.14
    rawn
    -0.13
     Rud
    -0.13
    eur
    -0.13
     *)((
    -0.13
    115
    -0.13
    uppies
    -0.13
     Rat
    -0.13
    POSITIVE LOGITS
     thereby
    0.20
     thus
    0.19
    inerary
    0.19
     should
    0.18
    thus
    0.17
     therefore
    0.17
    alic
    0.17
    should
    0.16
    zel
    0.16
     böylece
    0.15
    Activations Density 0.148%

    No Known Activations