© 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. 9-LLAMASCOPE-RES-131K
    11. 98955
    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
    sth
    -0.07
    arsers
    -0.07
    uyu
    -0.07
    iaux
    -0.07
    estre
    -0.07
    TEGER
    -0.07
    ics
    -0.07
    à¹Ĥà¸Ĺ
    -0.06
    estone
    -0.06
    ucci
    -0.06
    POSITIVE LOGITS
    ehr
    0.07
    decrypt
    0.06
    ิà¸Ķà¸ķ
    0.06
    ÑĤал
    0.06
    翼
    0.06
    rea
    0.06
    ayım
    0.06
    çĨŁ
    0.06
    æ¶
    0.06
    ippet
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.