© 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. 118839
    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
    ibbon
    -0.07
    ales
    -0.06
    .cls
    -0.06
    EDA
    -0.06
    NL
    -0.06
    ormal
    -0.06
    º
    -0.06
    yme
    -0.06
    rah
    -0.06
    ensa
    -0.06
    POSITIVE LOGITS
    ALTH
    0.07
    ARGET
    0.07
    alth
    0.07
    jang
    0.07
     meltdown
    0.06
    linger
    0.06
    (/^\
    0.06
    omed
    0.06
    ippi
    0.06
     Koch
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.