© 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. 42603
    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
    ÑĢава
    -0.10
    rok
    -0.08
    zos
    -0.08
    iglia
    -0.07
    apesh
    -0.07
    QRST
    -0.07
     diseñador
    -0.07
    enton
    -0.07
    ourg
    -0.07
    -mf
    -0.07
    POSITIVE LOGITS
     BaseType
    0.06
     semi
    0.06
    And
    0.06
     And
    0.05
     External
    0.05
     Cummings
    0.05
    304
    0.05
     OK
    0.05
    abin
    0.05
    ips
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.