© 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. 96159
    Prev
    Next
    INDEX
    Explanations

    URLs or references to online scientific articles

    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
    uos
    -0.07
    inson
    -0.07
    ehler
    -0.07
    uo
    -0.07
    boro
    -0.07
    odge
    -0.07
    QRS
    -0.06
    οÏįÏĤ
    -0.06
    fol
    -0.06
    íıŃ
    -0.06
    POSITIVE LOGITS
    lander
    0.07
    atego
    0.06
    .RunWith
    0.06
    大åħ¨
    0.06
    Segue
    0.06
    razier
    0.06
    787
    0.06
    oggle
    0.06
     Elo
    0.06
    Pool
    0.05
    Activations Density 0.001%

    No Known Activations