© 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. 120444
    Prev
    Next
    INDEX
    Explanations

    instances of error handling keywords in programming contexts

    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
    ussen
    -0.07
    etti
    -0.06
    Ľi
    -0.06
    _IR
    -0.06
    azing
    -0.06
     hone
    -0.06
    ourcem
    -0.06
    κοÏį
    -0.06
    zap
    -0.06
    žÃŃ
    -0.06
    POSITIVE LOGITS
    :↵
    0.07
    EOF
    0.06
    olic
    0.06
     Hutch
    0.06
    íĮĮ
    0.06
    ANTE
    0.06
    :')
    0.06
    LLL
    0.06
    aft
    0.06
    ward
    0.06
    Activations Density 0.001%

    No Known Activations