© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 1467
    Prev
    Next
    INDEX
    Explanations

    words starting with ex

    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
    plode
    -0.11
    /export
    -0.10
    ignant
    -0.10
    plorer
    -0.10
    pressor
    -0.10
    vest
    -0.10
    clude
    -0.09
     sham
    -0.09
    hani
    -0.09
    crease
    -0.09
    POSITIVE LOGITS
     offic
    0.12
     parte
    0.12
    erts
    0.12
    oner
    0.12
    haus
    0.12
     situ
    0.12
     cath
    0.12
    ogenous
    0.12
     mach
    0.12
    fol
    0.11
    Activations Density 0.039%

    No Known Activations