© 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. 1808
    Prev
    Next
    INDEX
    Explanations

    words related to types of spiritual or supernatural entities

    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
    oufl
    -0.07
    avanaugh
    -0.07
     Nash
    -0.07
    quets
    -0.07
    missions
    -0.06
    inou
    -0.06
    ouser
    -0.06
    OffsetTable
    -0.06
    apot
    -0.06
    tring
    -0.06
    POSITIVE LOGITS
    ud
    0.06
    ẻ
    0.06
     Pol
    0.06
    .Instance
    0.06
    aver
    0.06
     attent
    0.06
     Beard
    0.06
    cap
    0.06
     Univers
    0.05
    ãĥ«ãĥī
    0.05
    Activations Density 0.001%

    No Known Activations