© 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. 70205
    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
    724
    -0.07
    171
    -0.07
    els
    -0.07
    695
    -0.07
    uss
    -0.06
    anian
    -0.06
    affen
    -0.06
    718
    -0.06
    ely
    -0.06
     Outline
    -0.06
    POSITIVE LOGITS
    ivery
    0.07
    odash
    0.07
    jedn
    0.07
    antasy
    0.07
    captures
    0.07
    éĩĩè´Ń
    0.06
    allery
    0.06
    ipse
    0.06
    ollen
    0.06
     ìĭłê·ľ
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.