© 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. 92044
    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
     smarty
    -0.08
     dilig
    -0.08
    asal
    -0.08
    éal
    -0.07
    Creature
    -0.07
    âĢ¦↵↵↵
    -0.07
    auga
    -0.07
    -alist
    -0.07
     âĹĦ
    -0.07
    ãģķãģ¾
    -0.07
    POSITIVE LOGITS
    978
    0.06
    pekt
    0.06
    084
    0.06
    UserCode
    0.06
     respectively
    0.05
    SPATH
    0.05
     alike
    0.05
    ials
    0.05
     us
    0.05
    ider
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.