© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 83909
    Prev
    Next
    INDEX
    Explanations

    numerical identifiers and references to creative professions or interests

    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
    tra
    -0.08
    icc
    -0.07
    æķ·
    -0.06
    avana
    -0.06
    idUser
    -0.06
    ulo
    -0.06
    ffi
    -0.06
    oner
    -0.06
    qua
    -0.06
    ardon
    -0.06
    POSITIVE LOGITS
    ibold
    0.08
    Ã¤ÃŁ
    0.07
    ário
    0.07
    345
    0.06
    deck
    0.06
    ario
    0.06
    ectl
    0.06
    RecognitionException
    0.06
    .opend
    0.06
    arians
    0.06
    Activations Density 0.000%

    No Known Activations