© 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. 18712
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to algorithms and mathematical precision

    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
     lately
    -0.06
     tons
    -0.06
    isses
    -0.06
     Schneider
    -0.06
     kinds
    -0.06
     Kids
    -0.06
    ResourceId
    -0.06
    zcze
    -0.06
    -fw
    -0.06
    ocaly
    -0.06
    POSITIVE LOGITS
    GENCY
    0.07
    ogo
    0.07
    ãĢ
    0.07
    ilog
    0.07
    outine
    0.06
    _firestore
    0.06
    æĶ
    0.06
    FOUNDATION
    0.06
    itoris
    0.06
    istrovstvÃŃ
    0.06
    Activations Density 0.001%

    No Known Activations