© 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. 78107
    Prev
    Next
    INDEX
    Explanations

    mentions of intellectual or artistic endeavors

    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
    itchens
    -0.08
    418
    -0.06
    anou
    -0.06
    prites
    -0.06
    asu
    -0.06
    998
    -0.06
    ł
    -0.06
     Loft
    -0.06
     Seit
    -0.06
    872
    -0.06
    POSITIVE LOGITS
    forge
    0.07
    .Escape
    0.07
    .FieldName
    0.07
    ãģıãĤĵ
    0.07
    .itemView
    0.07
    .datab
    0.06
    çŃĴ
    0.06
    venta
    0.06
     вк
    0.06
    _COD
    0.06
    Activations Density 0.000%

    No Known Activations