© 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. 88372
    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
    æŀ¶
    -0.06
    ityEngine
    -0.06
    220
    -0.05
     autoComplete
    -0.05
    891
    -0.05
     Becker
    -0.05
     Fell
    -0.05
    feit
    -0.05
     befind
    -0.05
    ÙĬØ´
    -0.05
    POSITIVE LOGITS
    gratis
    0.09
    $MESS
    0.08
    $LANG
    0.08
    оÑĢож
    0.07
     Tarif
    0.07
    wang
    0.07
    ì§ĢëıĦ
    0.07
    *)_
    0.07
     آزÙħ
    0.07
     staffer
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.