© 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. 123254
    Prev
    Next
    INDEX
    Explanations

    symbols or punctuation marks

    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
    ostel
    -0.08
    uvre
    -0.06
    olet
    -0.06
    rego
    -0.06
    elaide
    -0.06
     Tong
    -0.06
    phem
    -0.06
    apan
    -0.06
     Trials
    -0.06
    ________
    -0.06
    POSITIVE LOGITS
    루
    0.07
    _Store
    0.07
    HLT
    0.07
    WithOptions
    0.07
    idor
    0.07
    laÅŁma
    0.07
    รà¸ĩ
    0.06
    xor
    0.06
    CHAIN
    0.06
     çal
    0.06
    Activations Density 0.000%

    No Known Activations