© 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. 5986
    Prev
    Next
    INDEX
    Explanations

    phrases indicating difficulty or capability in a task

    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
     emergency
    -0.07
     anti
    -0.07
     bud
    -0.06
    GO
    -0.06
     definition
    -0.06
     Anti
    -0.06
     stuff
    -0.06
     goto
    -0.06
     Peter
    -0.05
     my
    -0.05
    POSITIVE LOGITS
    afs
    0.08
    ãĥįãĥ«
    0.07
    amac
    0.07
    _reading
    0.07
    ÑĢей
    0.07
    panion
    0.07
    veloper
    0.07
    ffield
    0.07
    æĢ
    0.07
    istrovstvÃŃ
    0.07
    Activations Density 0.001%

    No Known Activations