© 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. 106725
    Prev
    Next
    INDEX
    Explanations

    instances of increment operations in 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
    rad
    -0.07
    rich
    -0.06
    μμα
    -0.06
    RATE
    -0.06
    VO
    -0.06
     boo
    -0.06
    ="__
    -0.06
    меÑĩ
    -0.06
    olem
    -0.06
     maxLength
    -0.06
    POSITIVE LOGITS
    æŀļ
    0.07
    abis
    0.07
     Volk
    0.06
     Pac
    0.06
    EDI
    0.06
     CIF
    0.06
    erah
    0.06
    inus
    0.06
    IPA
    0.06
    lege
    0.06
    Activations Density 0.003%

    No Known Activations