© 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. 53954
    Prev
    Next
    INDEX
    Explanations

    dialogue and quotes in text

    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
    actionDate
    -0.08
    styleType
    -0.07
    matchCondition
    -0.07
    egot
    -0.07
    оÑģлав
    -0.07
    Å¡em
    -0.07
    abit
    -0.07
    ulary
    -0.07
    219
    -0.07
     Sle
    -0.07
    POSITIVE LOGITS
    -of
    0.06
    ¦
    0.06
    aha
    0.06
    rah
    0.06
     pharm
    0.06
    ÂĢÂ
    0.06
    avian
    0.06
     Bart
    0.06
    IENT
    0.06
     Rank
    0.06
    Activations Density 0.066%

    No Known Activations