© 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. 104268
    Prev
    Next
    INDEX
    Explanations

    equality and assignment operators in programming code

    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
    esco
    -0.07
    lak
    -0.06
    ograd
    -0.06
    okrat
    -0.06
    coli
    -0.06
    rove
    -0.06
    enum
    -0.06
     stab
    -0.06
    geist
    -0.06
     ли
    -0.06
    POSITIVE LOGITS
    lan
    0.06
    æķ·
    0.06
     fox
    0.06
    ÃŃny
    0.06
    ä»ĭ
    0.06
    ä¸Ī
    0.06
    etch
    0.06
    dbg
    0.06
    à¹Īà¸Ńà¸ĩ
    0.06
    fts
    0.06
    Activations Density 0.000%

    No Known Activations