© 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. 14310
    Prev
    Next
    INDEX
    Explanations

    phrases indicating comparisons and evaluations

    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
    èĬ
    -0.08
    rier
    -0.07
    zi
    -0.07
    ritz
    -0.07
    हल
    -0.07
    unch
    -0.07
    _Version
    -0.07
    idon
    -0.07
    à¥įबर
    -0.06
    lok
    -0.06
    POSITIVE LOGITS
     PyTuple
    0.06
    buch
    0.06
    sst
    0.06
    remen
    0.06
     Booth
    0.06
    yas
    0.06
    quir
    0.06
    lech
    0.06
     Boiler
    0.06
    elter
    0.06
    Activations Density 0.021%

    No Known Activations