© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 63020
    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
    deaux
    -0.08
    LLU
    -0.06
     DEALINGS
    -0.06
    é¾Ħ
    -0.06
    clid
    -0.06
    ÛĮÙĨÚ©
    -0.06
     frase
    -0.06
    urat
    -0.06
    InstantiationException
    -0.06
    ADX
    -0.06
    POSITIVE LOGITS
     net
    0.07
    Ãłn
    0.07
    addock
    0.06
     excess
    0.06
    avid
    0.06
    amate
    0.06
    .ent
    0.06
     Hicks
    0.06
    zÄħd
    0.06
    票
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.