© 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. 81979
    Prev
    Next
    INDEX
    Explanations

    references to legal cases and court decisions

    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
    isspace
    -0.08
    emek
    -0.08
    loi
    -0.08
    andler
    -0.07
    ombo
    -0.07
    ãĥ¼ãĤ¹
    -0.07
    ÑĢÑĥн
    -0.07
    adiens
    -0.07
     à¤ĩतन
    -0.07
    anou
    -0.07
    POSITIVE LOGITS
     union
    0.09
     Shen
    0.06
    0.06
     kne
    0.06
     bes
    0.06
     Union
    0.06
     right
    0.06
     Labor
    0.06
     board
    0.06
     N
    0.06
    Activations Density 0.024%

    No Known Activations