© 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. 94207
    Prev
    Next
    INDEX
    Explanations

    occurrences of punctuation marks and their context within sentences

    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
    ogle
    -0.06
     Ce
    -0.06
    .getOwnProperty
    -0.05
    elves
    -0.05
     irrit
    -0.05
     Beg
    -0.05
    tracted
    -0.05
     Diaz
    -0.05
    ega
    -0.05
    tfoot
    -0.05
    POSITIVE LOGITS
    زب
    0.09
    ersist
    0.08
     endregion
    0.08
    лаж
    0.08
    æĤł
    0.07
    ãĥ¼ãĥĨ
    0.07
    rance
    0.07
    bij
    0.07
    odesk
    0.07
    _TYPED
    0.07
    Activations Density 0.004%

    No Known Activations