© 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 EvalsExportsAPI 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. 86076
    Prev
    Next
    INDEX
    Explanations

    conditional and assignment operators in programming code

    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
    leck
    -0.07
    ing
    -0.06
    reich
    -0.06
    neh
    -0.06
    sWith
    -0.06
    лиÑĤ
    -0.06
    rieb
    -0.06
     #__
    -0.06
    ÏĢη
    -0.06
    rie
    -0.06
    POSITIVE LOGITS
    ITOR
    0.08
    ----------------------------------------------------------------------
    0.07
    itor
    0.07
    conds
    0.07
    ëĦIJ
    0.07
    ÅŁa
    0.07
    ád
    0.07
    าà¸į
    0.07
    ÑĥÑī
    0.07
    ìĶ©
    0.07
    Activations Density 0.001%

    No Known Activations