© 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. 95621
    Prev
    Next
    INDEX
    Explanations

    configuration options within a programming or file setup context

    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
     |_
    -0.07
     rejected
    -0.07
     rejection
    -0.06
     Ingen
    -0.06
    udi
    -0.06
    %X
    -0.06
    phan
    -0.06
    hazi
    -0.06
    adin
    -0.06
    UTH
    -0.06
    POSITIVE LOGITS
     Holmes
    0.07
    CLE
    0.07
    ubyte
    0.06
    اعب
    0.06
    ItemCount
    0.06
    iên
    0.06
    _SPE
    0.06
     Vs
    0.06
     kotlinx
    0.06
     Cleveland
    0.06
    Activations Density 0.015%

    No Known Activations