© 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. 15-LLAMASCOPE-RES-131K
    11. 86115
    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
    Negative Logits
    ÄįÃŃ
    -0.08
     Alic
    -0.07
    glob
    -0.07
    omba
    -0.07
    ãĤŃãĥ³ãĤ°
    -0.07
    erna
    -0.07
    oron
    -0.07
    æ¤
    -0.07
    áp
    -0.07
    iggins
    -0.07
    POSITIVE LOGITS
     verbally
    0.06
     Gil
    0.06
     hugely
    0.05
     tom
    0.05
     himself
    0.05
    Gil
    0.05
    aque
    0.05
     apart
    0.05
     bott
    0.05
     obsess
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.