© 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. 18711
    Prev
    Next
    INDEX
    Explanations

    elements related to specific programming or data structures in a transaction context

    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
    gne
    -0.08
    ffen
    -0.07
    esser
    -0.07
     recep
    -0.07
    ród
    -0.07
    .listen
    -0.07
    ItemAt
    -0.07
    igators
    -0.07
     è¾
    -0.07
    .gmail
    -0.07
    POSITIVE LOGITS
    ash
    0.06
     patron
    0.06
    -Origin
    0.06
    age
    0.06
     AMS
    0.06
    ACS
    0.06
     Ober
    0.06
    osu
    0.06
     Ash
    0.06
    æĿ¥æºIJ
    0.06
    Activations Density 0.005%

    No Known Activations