© 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. 40610
    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
    Safety
    -0.06
     Safety
    -0.06
    Å¡ti
    -0.06
    ácil
    -0.06
    ëĭ¬
    -0.06
    vier
    -0.06
    oS
    -0.06
     Dell
    -0.06
    _consts
    -0.06
    åĨł
    -0.06
    POSITIVE LOGITS
    .disable
    0.06
    ora
    0.06
    ary
    0.06
     ç¦
    0.06
    -ui
    0.06
     McCart
    0.06
    μή
    0.06
    uv
    0.06
    åĭ
    0.06
     atIndex
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.