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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 33929
    Prev
    Next
    INDEX
    Explanations

    really good

    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
    mue
    -0.09
    494
    -0.09
     Hed
    -0.09
    ãģĿãĤĮãģ¯
    -0.09
     yes
    -0.09
     now
    -0.09
     happen
    -0.08
     ìĿ´ëĬĶ
    -0.08
     Barcl
    -0.08
    .synthetic
    -0.08
    POSITIVE LOGITS
     pretty
    0.26
    æĮº
    0.20
     really
    0.19
    pretty
    0.19
     fairly
    0.17
    retty
    0.17
     quite
    0.15
     definitely
    0.14
     Pretty
    0.14
    Pretty
    0.13
    Activations Density 0.073%

    No Known Activations