© 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. 76957
    Prev
    Next
    INDEX
    Explanations

    references to scientific research infrastructure and initiatives

    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
     show
    -0.06
    empo
    -0.06
     wind
    -0.06
     sight
    -0.06
     that
    -0.06
     trunk
    -0.06
    wind
    -0.06
     change
    -0.06
     say
    -0.06
     relationships
    -0.05
    POSITIVE LOGITS
     kullanıcı
    0.08
    facility
    0.08
    cry
    0.08
     Facility
    0.08
     facility
    0.08
     полÑĮзоваÑĤ
    0.08
     cry
    0.08
     Cry
    0.08
    /REC
    0.07
     пÑĢик
    0.07
    Activations Density 0.017%

    No Known Activations