© 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. 123263
    Prev
    Next
    INDEX
    Explanations

    phrases indicating actions, changes, or transitions

    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
    omik
    -0.08
    째
    -0.08
    elize
    -0.08
    .Uint
    -0.07
    Streamer
    -0.07
    ÙĩÙĨ
    -0.07
    rün
    -0.07
    ìĽĥ
    -0.07
    eldon
    -0.07
    idders
    -0.07
    POSITIVE LOGITS
     being
    0.07
    it
    0.07
    being
    0.06
    g
    0.06
     he
    0.06
    -being
    0.06
     authorities
    0.06
    upon
    0.06
     producer
    0.06
     publisher
    0.06
    Activations Density 0.026%

    No Known Activations