© 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. 27177
    Prev
    Next
    INDEX
    Explanations

    significant elements or components in various contexts, such as storytelling, visual elements, and social dynamics

    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
    822
    -0.07
    vero
    -0.07
    adh
    -0.07
    intptr
    -0.07
    ldr
    -0.07
    aho
    -0.07
    oder
    -0.07
    ancia
    -0.06
    825
    -0.06
    ÑģÑıÑĤ
    -0.06
    POSITIVE LOGITS
     being
    0.10
    being
    0.09
     sendo
    0.08
    Being
    0.07
     emphasis
    0.07
     intact
    0.07
     Being
    0.07
     included
    0.06
     dict
    0.06
    Broken
    0.06
    Activations Density 0.093%

    No Known Activations