© 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. 4704
    Prev
    Next
    INDEX
    Explanations

    instances of coding syntax and structure related to vector manipulation in a programming context

    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
     Yön
    -0.07
    ÏĦÏĥ
    -0.07
    ruh
    -0.07
     Redistributions
    -0.07
    ares
    -0.07
    Unmarshaller
    -0.07
    actionDate
    -0.07
    ichick
    -0.07
    ilded
    -0.07
    _MR
    -0.07
    POSITIVE LOGITS
    izi
    0.06
    utow
    0.06
    öm
    0.06
    .setOutput
    0.05
     erk
    0.05
    ÑĤÑĢа
    0.05
    uyo
    0.05
    iment
    0.05
    erer
    0.05
     sát
    0.05
    Activations Density 0.007%

    No Known Activations