© 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. 76967
    Prev
    Next
    INDEX
    Explanations

    references to written communication or documentation

    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
    eker
    -0.08
     tÃŃm
    -0.07
    919
    -0.07
    eder
    -0.06
    xt
    -0.06
    _SITE
    -0.06
    ire
    -0.06
    ech
    -0.06
    åĽ
    -0.06
    obody
    -0.06
    POSITIVE LOGITS
    /by
    0.08
    iger
    0.07
    icie
    0.07
     DataRow
    0.06
    ifice
    0.06
    dated
    0.06
    Äĵ
    0.06
    .OnClickListener
    0.06
    iggins
    0.06
     signed
    0.06
    Activations Density 0.002%

    No Known Activations