© 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. 17-LLAMASCOPE-RES-131K
    11. 130667
    Prev
    Next
    INDEX
    Explanations

    references to processes, errors, and programming-related terms

    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
    ogan
    -0.07
     TMPro
    -0.07
     Heller
    -0.07
    oje
    -0.06
    outh
    -0.06
    (PR
    -0.06
    ãĤĵãģ¨
    -0.06
    encodeURIComponent
    -0.06
    ocab
    -0.06
    NullException
    -0.06
    POSITIVE LOGITS
    ',['../
    0.07
    269
    0.06
    raquo
    0.06
    </
    0.06
     tá»Ń
    0.06
    apse
    0.06
     còn
    0.05
    dept
    0.05
    aylight
    0.05
     selectively
    0.05
    Activations Density 0.018%

    No Known Activations