© 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. 18472
    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
     poh
    -0.06
    zl
    -0.06
     provid
    -0.05
     cocoa
    -0.05
     pronto
    -0.05
    aga
    -0.05
     sh
    -0.05
     wa
    -0.05
     ‘
    -0.05
     Econ
    -0.05
    POSITIVE LOGITS
    è¶Ĭ
    0.07
    .xtext
    0.07
    adece
    0.07
    ervlet
    0.07
    apore
    0.07
     è¶
    0.06
    ICAST
    0.06
    ajo
    0.06
    CDF
    0.06
     gridColumn
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.