© 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. 79956
    Prev
    Next
    INDEX
    Explanations

    references to "global" concepts or parameters

    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
    plen
    -0.07
     Aires
    -0.07
    олÑİ
    -0.07
    кеÑĤ
    -0.07
    ResponseStatus
    -0.07
    angi
    -0.07
    emit
    -0.07
     ÐijолÑĮÑĪ
    -0.07
     içi
    -0.07
    ênh
    -0.07
    POSITIVE LOGITS
    /local
    0.08
    /global
    0.08
    entiful
    0.07
     Spare
    0.07
    mente
    0.07
     state
    0.07
    /public
    0.07
    bies
    0.06
    ized
    0.06
    bject
    0.06
    Activations Density 0.008%

    No Known Activations