© 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. 76266
    Prev
    Next
    INDEX
    Explanations

    references to personal and identifiable information

    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
    _EXPORT
    -0.07
    ERC
    -0.06
    rug
    -0.06
    θÎŃ
    -0.06
    fty
    -0.06
    맹
    -0.06
    hawk
    -0.06
    dong
    -0.06
     MOUSE
    -0.06
     Goose
    -0.06
    POSITIVE LOGITS
     eldre
    0.07
    urances
    0.07
    imed
    0.07
    ura
    0.07
    alm
    0.07
    krv
    0.07
    uries
    0.06
    aires
    0.06
    iam
    0.06
    uka
    0.06
    Activations Density 0.001%

    No Known Activations