© 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. 74042
    Prev
    Next
    INDEX
    Explanations

    references to divine or spiritual entities and their attributes

    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
    ment
    -0.06
     similarly
    -0.06
    en
    -0.06
    ine
    -0.06
    aper
    -0.06
    Æ°á»Ŀng
    -0.06
    o
    -0.05
    ien
    -0.05
     regard
    -0.05
    mere
    -0.05
    POSITIVE LOGITS
    ectl
    0.08
    pii
    0.07
    Pragma
    0.07
    gnu
    0.07
    strup
    0.07
    ruta
    0.07
    -ves
    0.07
    ÅĻet
    0.07
    erus
    0.07
    ahat
    0.07
    Activations Density 0.053%

    No Known Activations