© 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. 120198
    Prev
    Next
    INDEX
    Explanations

    concepts related to divine authority and spiritual strength

    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
    LIC
    -0.07
    untu
    -0.07
    ovice
    -0.07
    amac
    -0.07
    antino
    -0.07
    åĴ²
    -0.07
    SOLE
    -0.07
    isay
    -0.07
    arella
    -0.07
    ordes
    -0.07
    POSITIVE LOGITS
     AB
    0.06
     Clarence
    0.06
    ddy
    0.06
    agers
    0.06
     Lion
    0.06
    erra
    0.06
    èĥĨ
    0.06
    usz
    0.05
    082
    0.05
     bol
    0.05
    Activations Density 0.008%

    No Known Activations