© 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. 41610
    Prev
    Next
    INDEX
    Explanations

    references to religious or spiritual commands

    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
    ifar
    -0.08
     Abed
    -0.07
    Ñģен
    -0.07
    afen
    -0.07
    _tel
    -0.07
    รà¸Ķ
    -0.07
    rale
    -0.07
    缤
    -0.07
    orris
    -0.07
    achel
    -0.07
    POSITIVE LOGITS
     UIG
    0.07
     Signs
    0.07
     Al
    0.06
     Tas
    0.06
     Alma
    0.06
    fir
    0.06
    l
    0.06
     Harvey
    0.06
     Ding
    0.06
    al
    0.05
    Activations Density 0.013%

    No Known Activations