© 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. 5786
    Prev
    Next
    INDEX
    Explanations

    instances of the word "reach" and its variants, indicating a focus on the concept of outreach or connection

    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
    onis
    -0.07
    chter
    -0.07
    go
    -0.07
     Casc
    -0.06
    ÑĪе
    -0.06
    opa
    -0.06
    linked
    -0.06
    ibble
    -0.06
    oj
    -0.06
     風
    -0.06
    POSITIVE LOGITS
    ÑĨÑĸ
    0.07
    .Messaging
    0.07
    annel
    0.07
    inel
    0.07
    ieve
    0.07
    vrier
    0.07
    STALL
    0.07
    رز
    0.07
    itulo
    0.06
     agreement
    0.06
    Activations Density 0.008%

    No Known Activations