© 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 EvalsExportsinterp-engineNEWAPI 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. 119879
    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
    iddi
    -0.07
    ãĥ³ãĤ¬
    -0.07
    諸
    -0.07
    hta
    -0.07
    gard
    -0.07
    rowable
    -0.07
    ãģĵãĤį
    -0.07
    amburger
    -0.07
    æŁ´
    -0.07
    .yy
    -0.07
    POSITIVE LOGITS
    acco
    0.06
    atel
    0.06
    lane
    0.06
    izzle
    0.06
    Lane
    0.06
    blas
    0.06
    iyeti
    0.06
    appers
    0.05
    arak
    0.05
    Monad
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.