© 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. 72484
    Prev
    Next
    INDEX
    Explanations

    references to health risks and medical conditions

    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
    iu
    -0.07
    itest
    -0.06
     Severity
    -0.06
     dosy
    -0.06
    Fault
    -0.06
    Severity
    -0.06
    sav
    -0.06
    ände
    -0.06
    472
    -0.06
    cele
    -0.06
    POSITIVE LOGITS
     outright
    0.09
     loss
    0.08
     ultimately
    0.08
     increased
    0.08
     potentially
    0.07
     even
    0.07
    deo
    0.07
     downright
    0.06
     permanent
    0.06
    loss
    0.06
    Activations Density 0.038%

    No Known Activations