© 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. 119292
    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
    zek
    -0.07
    UTF
    -0.07
    ynom
    -0.06
    ABC
    -0.06
    amment
    -0.06
    enza
    -0.06
    FB
    -0.06
     fam
    -0.06
    UIS
    -0.06
    infra
    -0.06
    POSITIVE LOGITS
    AILS
    0.07
    ãĥ¼ãĥ«ãĥī
    0.07
    iken
    0.06
    orado
    0.06
    δη
    0.06
    aley
    0.06
    ëłĪìĬ¤
    0.06
     reel
    0.06
    ëł
    0.06
     лак
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.