© 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. 30621
    Prev
    Next
    INDEX
    Explanations

    inquiries about medical conditions or treatments and their implications

    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
     indeed
    -0.07
     both
    -0.07
     perhaps
    -0.07
     http
    -0.06
    .persist
    -0.06
     Patel
    -0.06
     many
    -0.06
     www
    -0.06
     quite
    -0.06
     Peterson
    -0.06
    POSITIVE LOGITS
    ?↵
    0.08
     dál
    0.08
    alim
    0.07
    ï¼Ł↵
    0.07
    )?↵
    0.07
    elu
    0.07
    ?>>
    0.07
    exion
    0.07
    ÐĽÐ¬
    0.07
     bát
    0.06
    Activations Density 0.025%

    No Known Activations