© 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. 60758
    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
    spi
    -0.08
    /Instruction
    -0.07
    éĩ
    -0.07
    odia
    -0.07
    lea
    -0.07
    .compiler
    -0.07
    uD
    -0.06
    ục
    -0.06
    csr
    -0.06
    üs
    -0.06
    POSITIVE LOGITS
    让æĪij
    0.07
     saya
    0.07
     minha
    0.07
    ç»ĻæĪij
    0.07
     myself
    0.07
     my
    0.07
    اض
    0.06
    .literal
    0.06
    UAGE
    0.06
    zig
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.