© 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. 30632
    Prev
    Next
    INDEX
    Explanations

    references to religious or spiritual themes

    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
    odos
    -0.06
    egie
    -0.06
    UMB
    -0.06
    ATTER
    -0.06
    uess
    -0.06
    void
    -0.06
     Kimber
    -0.06
    ä½łä»¬
    -0.06
     caution
    -0.05
    .TR
    -0.05
    POSITIVE LOGITS
    owell
    0.08
     Ply
    0.07
    inic
    0.07
    asz
    0.07
    hay
    0.07
    angler
    0.07
    oho
    0.06
    owel
    0.06
    hani
    0.06
    /autoload
    0.06
    Activations Density 0.002%

    No Known Activations