© 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. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 31902
    Prev
    Next
    INDEX
    Explanations

    hydroxide conductivity mS/cm

    np_acts-logits-general · gemini-2.5-flash-lite

    technical or scientific notation, particularly units of measurement and chemical/scientific terminology.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @yooniel31
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf
    Configuration
    Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt
    Prompts (Dashboard)
    10,000 prompts, 128 tokens each
    Dataset (Dashboard)
    lmsys/lmsys-chat-1m
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mechanics
    -0.10
     stalled
    -0.09
     magnets
    -0.09
     sick
    -0.09
     Garc
    -0.09
    ué
    -0.09
    aura
    -0.09
     trib
    -0.09
    oub
    -0.09
     elasticity
    -0.09
    POSITIVE LOGITS
     conduct
    0.35
     Conduct
    0.30
    conduct
    0.28
     conducting
    0.26
     conducts
    0.24
     пÑĢовод
    0.22
    导
    0.20
     conducted
    0.19
     conduc
    0.19
     conductor
    0.19
    Activations Density 0.069%

    No Known Activations