© 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. 15037
    Prev
    Next
    INDEX
    Explanations

    mentions of death or significant loss

    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
    رس
    -0.08
    indsight
    -0.07
    oi
    -0.07
    ÏĥÏĩ
    -0.07
    emes
    -0.07
    _ABI
    -0.07
    سÙħØ©
    -0.07
    омен
    -0.07
    celik
    -0.07
    -DD
    -0.07
    POSITIVE LOGITS
     died
    0.14
     death
    0.12
     dies
    0.11
     deaths
    0.11
     die
    0.11
     dying
    0.10
     dead
    0.10
     killed
    0.09
    _die
    0.09
    death
    0.08
    Activations Density 0.184%

    No Known Activations