© 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. 83354
    Prev
    Next
    INDEX
    Explanations

    inquiries or requests for additional information

    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
    antal
    -0.06
    okus
    -0.06
    наÑĢ
    -0.06
    heimer
    -0.06
    kara
    -0.06
    imple
    -0.06
    enin
    -0.05
    ayan
    -0.05
     declining
    -0.05
     vic
    -0.05
    POSITIVE LOGITS
    anik
    0.08
    iani
    0.07
     knowing
    0.07
    abella
    0.07
    Marshal
    0.07
    añ
    0.07
     Aux
    0.07
    isini
    0.07
    /vector
    0.07
    OWER
    0.07
    Activations Density 0.005%

    No Known Activations