© 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. 16293
    Prev
    Next
    INDEX
    Explanations

    references to mysterious or enigmatic subjects or situations

    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
    eria
    -0.07
    ÑĥÑĩа
    -0.07
    à¥Ģय
    -0.07
    каÑģ
    -0.06
    .bp
    -0.06
    _PIX
    -0.06
    ãģ¡ãĤĥ
    -0.06
     Colony
    -0.06
    .scalablytyped
    -0.06
    ÙģØ´
    -0.06
    POSITIVE LOGITS
    ness
    0.14
    ly
    0.11
    LY
    0.09
    ely
    0.08
    ariat
    0.08
    nes
    0.08
    -looking
    0.08
    /conf
    0.08
    NESS
    0.08
    mente
    0.07
    Activations Density 0.007%

    No Known Activations