© 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. 54754
    Prev
    Next
    INDEX
    Explanations

    information related to nuclear testing and 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
     sexual
    -0.07
     antenn
    -0.06
     Sexual
    -0.06
     dro
    -0.06
     Demand
    -0.06
    agi
    -0.05
     Gill
    -0.05
    ÙĪار
    -0.05
    fty
    -0.05
    _visibility
    -0.05
    POSITIVE LOGITS
    wap
    0.08
    Reusable
    0.08
     fiss
    0.08
    Ìģc
    0.07
    ¨¨
    0.07
    oeff
    0.07
    imas
    0.07
     deton
    0.07
    _suite
    0.07
    uraa
    0.07
    Activations Density 0.007%

    No Known Activations