© 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. 72439
    Prev
    Next
    INDEX
    Explanations

    references to terrorism and biological weapons

    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
     cref
    -0.06
     trapped
    -0.06
    :void
    -0.06
     Tip
    -0.06
    ASC
    -0.06
    Tip
    -0.06
    unal
    -0.06
    utral
    -0.05
    ifty
    -0.05
    806
    -0.05
    POSITIVE LOGITS
     poisoning
    0.08
    uju
    0.07
     chemical
    0.07
    aceous
    0.07
     Poison
    0.07
     poisoned
    0.07
    iddles
    0.07
     Mits
    0.07
    Ñİк
    0.07
    iw
    0.06
    Activations Density 0.001%

    No Known Activations