© 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. 81157
    Prev
    Next
    INDEX
    Explanations

    references to death and the supernatural

    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
     addCriterion
    -0.09
    amerate
    -0.08
    .Magic
    -0.08
    orado
    -0.07
    Indented
    -0.07
    alette
    -0.07
    ëĿ
    -0.07
     Králové
    -0.07
    oslav
    -0.07
    ÅĻÃŃzenÃŃ
    -0.07
    POSITIVE LOGITS
     Death
    0.12
     death
    0.11
    Death
    0.10
    death
    0.09
    -death
    0.08
     Deaths
    0.07
     deaths
    0.07
    çµ±
    0.07
     Ferry
    0.07
    _death
    0.06
    Activations Density 0.052%

    No Known Activations