© 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. 9-LLAMASCOPE-RES-131K
    11. 97061
    Prev
    Next
    INDEX
    Explanations

    references to code structure and dependencies in programming

    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
    SENT
    -0.06
    MBED
    -0.06
    apot
    -0.06
     bare
    -0.06
     pot
    -0.06
     anom
    -0.06
    ynn
    -0.06
    ç¯
    -0.06
     Ùħؤ
    -0.06
    sen
    -0.05
    POSITIVE LOGITS
     -*-č↵
    0.08
    ees
    0.07
     navr
    0.07
     poil
    0.07
    haven
    0.07
    abase
    0.07
    _vi
    0.07
    kud
    0.07
    ipse
    0.07
    ayne
    0.07
    Activations Density 0.002%

    No Known Activations