© 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. 36258
    Prev
    Next
    INDEX
    Explanations

    ste followed by specific endings

    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
    se
    -0.11
    ãģĦãģ¾ãģĻ
    -0.11
    ãģĬãĤĬ
    -0.10
    rait
    -0.09
    st
    -0.09
    688
    -0.09
    _bases
    -0.09
    itters
    -0.09
    342
    -0.08
    usc
    -0.08
    POSITIVE LOGITS
     ste
    0.18
    aming
    0.15
    alth
    0.13
    amed
    0.12
    áf
    0.11
    acie
    0.11
    ved
    0.11
    enson
    0.11
    ered
    0.11
    akh
    0.11
    Activations Density 0.029%

    No Known Activations