© 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. 54029
    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
    qual
    -0.07
    ãģĦ
    -0.06
     Vog
    -0.06
    Advertisement
    -0.06
     ÄĮes
    -0.05
    ãģĬ
    -0.05
    -0.05
     Advertisement
    -0.05
     nop
    -0.05
    à¹Ĥ
    -0.05
    POSITIVE LOGITS
    -automatic
    0.08
     defaulted
    0.07
    orpion
    0.07
    _UNDEF
    0.07
    automatic
    0.07
    ейÑģÑĤв
    0.07
    entlich
    0.07
    ãģĵãģ¡ãĤī
    0.07
    ñana
    0.07
    znik
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.