© 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 EvalsExportsAPI 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. 58656
    Prev
    Next
    INDEX
    Explanations

    mentions of events, appearances, and involvements in public speaking or presentations

    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
    ardy
    -0.08
    reich
    -0.07
    سد
    -0.07
    Pok
    -0.07
    adera
    -0.07
    tr
    -0.07
    ÐŁÐļ
    -0.06
    ê·¸ëŁ¬
    -0.06
    ÙĬÙĥا
    -0.06
    ÅĻÃŃd
    -0.06
    POSITIVE LOGITS
    olare
    0.07
    itag
    0.07
    iem
    0.07
    ayah
    0.07
    endcode
    0.06
    ugar
    0.06
     fø
    0.06
    ibt
    0.06
     alongside
    0.06
     participate
    0.06
    Activations Density 0.028%

    No Known Activations