© 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. 9-LLAMASCOPE-RES-131K
    11. 97347
    Prev
    Next
    INDEX
    Explanations

    elements related to organizational structures and member leagues in the context of roller derby

    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
    ertz
    -0.08
    pron
    -0.07
    laus
    -0.07
     pron
    -0.06
    ombo
    -0.06
    Fld
    -0.06
    ilir
    -0.06
    ulur
    -0.06
    uddle
    -0.06
    IRE
    -0.06
    POSITIVE LOGITS
    ocale
    0.08
    onso
    0.06
    allas
    0.06
    ãĤ¸ãĤª
    0.06
    /gtest
    0.06
    ipur
    0.06
    fst
    0.06
    opher
    0.06
     accuse
    0.06
    obby
    0.06
    Activations Density 0.015%

    No Known Activations