© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 30053
    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
     Haram
    -0.07
    rollable
    -0.07
    ô
    -0.07
    avage
    -0.06
    ÏĢÏĮ
    -0.06
    ottes
    -0.06
    PF
    -0.06
    IFF
    -0.06
     Mane
    -0.06
     ÐIJнд
    -0.06
    POSITIVE LOGITS
    esium
    0.07
    arov
    0.06
    egie
    0.06
    atham
    0.06
    agine
    0.06
    lea
    0.06
    globals
    0.06
     communications
    0.06
    .opensource
    0.06
     Cassidy
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.