© 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. 119170
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    oub
    -0.06
    otec
    -0.06
    uai
    -0.06
     Stam
    -0.06
    stit
    -0.06
    aul
    -0.06
     alphabet
    -0.06
    iddy
    -0.06
    uffers
    -0.06
    alphabet
    -0.06
    POSITIVE LOGITS
    ToLocal
    0.08
    530
    0.08
    ador
    0.07
    udson
    0.06
    èĥ¶
    0.06
     пÑĸдÑģ
    0.06
    298
    0.06
     Retro
    0.06
    croft
    0.06
    çĺ
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.