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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 84576
    Prev
    Next
    INDEX
    Explanations

    punctuations and end-of-statement markers in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    imb
    -0.06
    etik
    -0.06
    ">//
    -0.06
    utton
    -0.06
    _aux
    -0.06
    .scalablytyped
    -0.06
    Io
    -0.06
    CLU
    -0.06
    kin
    -0.06
     Humb
    -0.06
    POSITIVE LOGITS
     setattr
    0.08
    setattr
    0.08
    apy
    0.08
     shar
    0.06
    icens
    0.06
    оза
    0.06
    ạch
    0.06
     Campos
    0.06
    emean
    0.06
    á»ħ
    0.06
    Activations Density 0.028%

    No Known Activations