© 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. 30865
    Prev
    Next
    INDEX
    Explanations

    topics related to algorithm performance and optimization in mathematical contexts

    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
    rup
    -0.07
    ERV
    -0.06
     only
    -0.06
    -only
    -0.06
     Ak
    -0.06
     asympt
    -0.06
     ache
    -0.06
     fully
    -0.06
     pump
    -0.06
     identical
    -0.06
    POSITIVE LOGITS
    SizeMode
    0.07
     Relatives
    0.07
    gMaps
    0.07
     toJson
    0.07
    elor
    0.07
    極
    0.07
    æĹıèĩªæ²»
    0.06
     ЧаÑģ
    0.06
    FindObject
    0.06
     TMPro
    0.06
    Activations Density 0.019%

    No Known Activations