© 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. 9-LLAMASCOPE-RES-131K
    11. 99266
    Prev
    Next
    INDEX
    Explanations

    references to specific articles or notable figures in the literary field

    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
    inspace
    -0.07
    ici
    -0.07
    nap
    -0.06
    iff
    -0.06
    thouse
    -0.06
     Reeves
    -0.06
    rels
    -0.06
    arel
    -0.06
    ën
    -0.06
    .sg
    -0.06
    POSITIVE LOGITS
    riz
    0.08
    erah
    0.07
    alia
    0.07
    dda
    0.07
    ãģ¡ãĤī
    0.06
    abbo
    0.06
    .ManyToMany
    0.06
    ìĿ´ìĸ´
    0.06
    VID
    0.06
    evin
    0.06
    Activations Density 0.119%

    No Known Activations