© 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. 29236
    Prev
    Next
    INDEX
    Explanations

    soluble in water or solvents

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    adge
    -0.11
    615
    -0.09
    ensa
    -0.09
    674
    -0.09
    ago
    -0.09
    ahi
    -0.09
    rena
    -0.08
     alphabetical
    -0.08
    ena
    -0.08
    311
    -0.08
    POSITIVE LOGITS
    /misc
    0.14
     polar
    0.14
     sol
    0.14
     water
    0.14
     Sol
    0.13
    .sol
    0.12
     Polar
    0.12
    uble
    0.11
    ugins
    0.11
    ility
    0.10
    Activations Density 0.010%

    No Known Activations