© 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. 1299
    Prev
    Next
    INDEX
    Explanations

    references to administrative actions and roles

    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
    ori
    -0.07
    až
    -0.07
    405
    -0.06
    atz
    -0.06
    ehen
    -0.06
    örü
    -0.06
    목
    -0.06
    ifar
    -0.06
     Fork
    -0.06
     sooner
    -0.05
    POSITIVE LOGITS
    $MESS
    0.07
     Grimm
    0.07
    .datab
    0.07
    chod
    0.06
    InternalServerError
    0.06
    Dot
    0.06
     تاب
    0.06
    oa
    0.06
    avors
    0.06
     (::
    0.06
    Activations Density 0.000%

    No Known Activations