© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 26401
    Prev
    Next
    INDEX
    Explanations

    programming syntax related to function declarations and data management

    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
    ãģ¨ãģĨ
    -0.07
    urat
    -0.07
    outil
    -0.06
    469
    -0.06
    _opts
    -0.06
    ãĤ§
    -0.06
    лам
    -0.06
    /theme
    -0.06
     Micro
    -0.06
    ãĥ¼ãĥĹ
    -0.06
    POSITIVE LOGITS
     reverse
    0.08
    reverse
    0.07
    Reverse
    0.07
     inverse
    0.07
     Reverse
    0.07
     reversed
    0.06
     reversing
    0.06
    Inverse
    0.06
     ngược
    0.06
    ilk
    0.06
    Activations Density 0.016%

    No Known Activations