© 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. 56401
    Prev
    Next
    INDEX
    Explanations

    references to doors, closures, and confinement

    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
    ghi
    -0.06
     Bri
    -0.06
    strup
    -0.06
    nesc
    -0.06
     addCriterion
    -0.06
    atri
    -0.06
    istrovstvÃŃ
    -0.06
    ison
    -0.06
    916
    -0.06
    ÅĽÄĩ
    -0.06
    POSITIVE LOGITS
     lock
    0.08
     locks
    0.08
     locking
    0.08
    locks
    0.07
     shut
    0.07
    closed
    0.07
     locked
    0.07
    à¹Ħว
    0.07
     Lock
    0.07
    -lock
    0.07
    Activations Density 0.009%

    No Known Activations