© 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. 38430
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the aims or purposes of studies or research

    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
    ýt
    -0.07
    en
    -0.06
    quil
    -0.06
    ug
    -0.06
    ÑīеÑģÑĤв
    -0.06
    asel
    -0.06
    suz
    -0.06
    marked
    -0.06
    kol
    -0.06
    net
    -0.06
    POSITIVE LOGITS
     this
    0.09
    ipt
    0.08
    ivec
    0.07
     article
    0.07
    esson
    0.07
    essa
    0.07
    Escort
    0.06
    Ī¬
    0.06
    ainer
    0.06
    /scripts
    0.06
    Activations Density 0.009%

    No Known Activations