© 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. 31574
    Prev
    Next
    INDEX
    Explanations

    words starting with f, r, or c

    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
     Flush
    -0.11
    gamber
    -0.10
    evin
    -0.10
     flush
    -0.10
    ieve
    -0.10
    emann
    -0.09
     zap
    -0.09
     reve
    -0.09
    çķĻ
    -0.09
     prov
    -0.09
    POSITIVE LOGITS
    actory
    0.14
    CTOR
    0.12
    iltr
    0.11
    olet
    0.11
    idious
    0.11
    hook
    0.11
    inand
    0.10
    uenta
    0.10
    oje
    0.10
    ordable
    0.10
    Activations Density 0.095%

    No Known Activations