© 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. 17408
    Prev
    Next
    INDEX
    Explanations

    expressions of desire or interest in purchasing something

    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
    Ñıми
    -0.07
     Vander
    -0.07
    سÙĬ
    -0.06
    знаÑĩа
    -0.06
     indeb
    -0.06
    loy
    -0.06
    hem
    -0.06
    zew
    -0.06
    ipsis
    -0.06
     Gazette
    -0.06
    POSITIVE LOGITS
    624
    0.07
    ÑĤен
    0.07
    onya
    0.07
    IRR
    0.06
    arry
    0.06
    463
    0.06
    âĢª
    0.06
    583
    0.06
    224
    0.06
    stantiate
    0.06
    Activations Density 0.015%

    No Known Activations