© 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. 116677
    Prev
    Next
    INDEX
    Explanations

    references to data collection and user privacy

    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
    arrison
    -0.08
    повÑĸд
    -0.07
    ÏĦεÏħ
    -0.07
    ansi
    -0.07
     IonicModule
    -0.07
    ยา
    -0.07
    ạt
    -0.07
    ymm
    -0.07
    ìľ¡
    -0.07
    ợ
    -0.07
    POSITIVE LOGITS
    -automatic
    0.07
     collect
    0.06
     automatic
    0.06
     suck
    0.06
     Cookies
    0.06
     cookies
    0.06
    ovi
    0.06
     tal
    0.06
    agna
    0.06
     gather
    0.05
    Activations Density 0.002%

    No Known Activations