© 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. 91660
    Prev
    Next
    INDEX
    Explanations

    disclaimers related to the limitations of information provided in documents

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    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
    967
    -0.07
    æŁ³
    -0.07
    urch
    -0.07
    766
    -0.06
    Themes
    -0.06
     Learned
    -0.06
    XR
    -0.06
    PIO
    -0.06
    гÑĢад
    -0.06
    owed
    -0.06
    POSITIVE LOGITS
     replace
    0.08
    ries
    0.08
     replaces
    0.08
     substitutes
    0.08
    replace
    0.08
     substitute
    0.07
     replacing
    0.07
    gua
    0.07
     advant
    0.07
    /fontawesome
    0.07
    Activations Density 0.006%

    No Known Activations