© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 69838
    Prev
    Next
    INDEX
    Explanations

    references to credit or attribution in a document

    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
    scape
    -0.07
    ONTAL
    -0.07
    ymoon
    -0.06
     Waterloo
    -0.06
    ancell
    -0.06
    loth
    -0.06
    panion
    -0.06
    ump
    -0.06
    anou
    -0.06
    anga
    -0.06
    POSITIVE LOGITS
    /templates
    0.07
     Dữ
    0.07
    ild
    0.06
     dur
    0.06
    ICENSE
    0.06
     Conte
    0.06
    viso
    0.06
     exercise
    0.06
     ÑĥÑģÑĤ
    0.06
     Comet
    0.06
    Activations Density 0.002%

    No Known Activations