© 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. 95953
    Prev
    Next
    INDEX
    Explanations

    terms related to specific individuals and educational institutions

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    å¾Ĵ
    -0.07
    esson
    -0.07
    isos
    -0.07
    azon
    -0.07
    anos
    -0.07
    ateurs
    -0.06
     eens
    -0.06
    ίγ
    -0.06
    bery
    -0.06
    arya
    -0.06
    POSITIVE LOGITS
    indre
    0.08
    oth
    0.07
    jamin
    0.07
    431
    0.07
    upported
    0.07
    olution
    0.07
    ży
    0.07
     uf
    0.07
    ient
    0.07
     ux
    0.07
    Activations Density 0.006%

    No Known Activations