© 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 EvalsExportsAPI 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. 56017
    Prev
    Next
    INDEX
    Explanations

    references to legal orders or documents

    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
    &P
    -0.07
    izza
    -0.06
    roperties
    -0.06
    &D
    -0.06
     Brass
    -0.06
    createClass
    -0.06
     King
    -0.06
    claimer
    -0.05
    king
    -0.05
     (=
    -0.05
    POSITIVE LOGITS
    oi
    0.07
    orex
    0.07
    idl
    0.07
     lao
    0.07
    OI
    0.07
    abra
    0.07
    continent
    0.06
    æ§
    0.06
    .Override
    0.06
    agua
    0.06
    Activations Density 0.000%

    No Known Activations