© 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. 87449
    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
    yan
    -0.06
    545
    -0.06
    ych
    -0.06
    atem
    -0.06
    ingu
    -0.06
    ard
    -0.06
    scr
    -0.05
    cess
    -0.05
    lique
    -0.05
     gal
    -0.05
    POSITIVE LOGITS
    .gpu
    0.08
    .opend
    0.07
    /drivers
    0.07
     Ala
    0.07
    <quote
    0.07
    ãģ£ãģ±
    0.07
    ndl
    0.07
    aversable
    0.06
    recht
    0.06
    GetInstance
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.