© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 45296
    Prev
    Next
    INDEX
    Explanations

    is/was/were followed by descriptions

    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
     Wan
    -0.10
    hiro
    -0.09
     hes
    -0.09
    uant
    -0.09
     Graves
    -0.09
     gamm
    -0.09
     Poz
    -0.08
     feeling
    -0.08
     pussy
    -0.08
     Voll
    -0.08
    POSITIVE LOGITS
     willing
    0.18
     always
    0.18
     often
    0.16
     partial
    0.15
    always
    0.14
    常
    0.14
     known
    0.14
     constantly
    0.14
     willingness
    0.13
     Always
    0.13
    Activations Density 0.070%

    No Known Activations