© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 39930
    Prev
    Next
    INDEX
    Explanations

    programming keywords related to constants and final variables 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
     rep
    -0.07
    ory
    -0.06
     Gems
    -0.06
    utz
    -0.06
    ussen
    -0.06
    ofil
    -0.06
    881
    -0.06
    ore
    -0.06
    ÑĤÑİ
    -0.06
     mist
    -0.06
    POSITIVE LOGITS
    ktop
    0.07
    ινÏĮ
    0.07
     int
    0.07
     Anc
    0.07
    tdown
    0.06
    ickness
    0.06
    ADE
    0.06
    Collapse
    0.06
    PED
    0.06
    LOSE
    0.06
    Activations Density 0.003%

    No Known Activations