© 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. 120840
    Prev
    Next
    INDEX
    Explanations

    patterns related to testing and assertions 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
    ALA
    -0.07
     unthinkable
    -0.06
     عب
    -0.06
    isine
    -0.06
    IVES
    -0.06
    (([
    -0.06
    enga
    -0.06
     ro
    -0.06
    _ASSUME
    -0.06
    .walk
    -0.06
    POSITIVE LOGITS
     count
    0.07
    logan
    0.07
    -count
    0.06
    entiful
    0.06
    âĢŀM
    0.06
    count
    0.06
    umer
    0.06
    steller
    0.06
    loha
    0.06
    =count
    0.06
    Activations Density 0.010%

    No Known Activations