© 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. 9-LLAMASCOPE-RES-131K
    11. 94143
    Prev
    Next
    INDEX
    Explanations

    technical programming and scripting references

    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
    aldi
    -0.08
    ÙİØ£
    -0.07
    Ñĸж
    -0.07
    frau
    -0.07
     addCriterion
    -0.07
    BOOLE
    -0.07
    HING
    -0.07
    /***/
    -0.07
    leitung
    -0.07
    .osgi
    -0.06
    POSITIVE LOGITS
    Member
    0.06
     or
    0.06
     turb
    0.06
    bris
    0.06
    ogan
    0.06
    =wx
    0.06
    浩
    0.06
     harmon
    0.06
    ocl
    0.06
    360
    0.06
    Activations Density 0.121%

    No Known Activations