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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 106160
    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
    irsch
    -0.06
    577
    -0.06
    est
    -0.06
     ga
    -0.06
     Illustrated
    -0.06
    .communication
    -0.06
    insky
    -0.06
     Ùħرک
    -0.06
    /testing
    -0.06
    eral
    -0.06
    POSITIVE LOGITS
     setFrame
    0.08
    .showMessageDialog
    0.07
    agem
    0.07
    epy
    0.07
     NONINFRINGEMENT
    0.07
    >manual
    0.06
    cente
    0.06
    istrovstvÃŃ
    0.06
    ieder
    0.06
    compat
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.