© 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. 79714
    Prev
    Next
    INDEX
    Explanations

    mentions of error and failure conditions in code documentation

    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
    iliz
    -0.07
    ÑģпÑĸлÑĮ
    -0.07
    antry
    -0.06
    esser
    -0.06
    uko
    -0.06
    ãĥ¼ãĥ«
    -0.06
    afil
    -0.06
    phin
    -0.06
     بع
    -0.06
    ÑĥÑĩ
    -0.06
    POSITIVE LOGITS
    y
    0.07
    rog
    0.07
    æĻ¯
    0.06
    rob
    0.06
    uly
    0.06
    743
    0.06
    medi
    0.05
    _SRC
    0.05
    ycop
    0.05
     chops
    0.05
    Activations Density 0.001%

    No Known Activations