© 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. 124562
    Prev
    Next
    INDEX
    Explanations

    instances of brackets and related syntax in programming or error log messages

    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
     Tyr
    -0.06
     Edwin
    -0.06
    rei
    -0.05
     Norte
    -0.05
    inky
    -0.05
    .o
    -0.05
    acre
    -0.05
    rych
    -0.05
     Arm
    -0.05
    tron
    -0.05
    POSITIVE LOGITS
    oftware
    0.08
     å°
    0.07
    dre
    0.07
    µ
    0.07
    AutoSize
    0.07
    Ð
    0.07
    ÑĶн
    0.07
    adan
    0.07
    bjerg
    0.07
    ÐķС
    0.07
    Activations Density 0.001%

    No Known Activations