© 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. 42659
    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
    	Copyright
    -0.08
    ivre
    -0.08
    ùa
    -0.07
    mts
    -0.07
    arna
    -0.07
    Ñıв
    -0.07
    engl
    -0.07
     Angus
    -0.07
    igo
    -0.07
    opsis
    -0.06
    POSITIVE LOGITS
     partly
    0.07
    خاÙĨ
    0.06
     mainly
    0.06
     Noble
    0.06
    .Names
    0.06
     their
    0.06
     nich
    0.06
    chr
    0.06
    694
    0.06
    .eval
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.