© 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. 81376
    Prev
    Next
    INDEX
    Explanations

    words related to responsibility or accountability

    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
    oli
    -0.06
     surprise
    -0.06
    лок
    -0.06
    nota
    -0.06
    åħĴ
    -0.06
    -or
    -0.06
    /rem
    -0.06
    æĥij
    -0.06
     Cookbook
    -0.06
    æ¡
    -0.06
    POSITIVE LOGITS
    pios
    0.07
     Bow
    0.07
    _GEN
    0.07
    ysize
    0.07
     Inch
    0.06
    ospace
    0.06
    cher
    0.06
    STYPE
    0.06
    omat
    0.06
    ÑīÑĸ
    0.06
    Activations Density 0.005%

    No Known Activations