© 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. 38749
    Prev
    Next
    INDEX
    Explanations

    specific nouns and actions

    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
    æĪĸèĢħ
    -0.09
    NR
    -0.09
    rette
    -0.09
     or
    -0.08
    æĪĸ
    -0.08
    /null
    -0.08
    /of
    -0.08
    ìĿ¸ìĿĦ
    -0.08
     или
    -0.08
     Äįi
    -0.08
    POSITIVE LOGITS
     whose
    0.11
    whose
    0.10
    åħ·æľī
    0.09
    ï¼Įåħ¶ä¸Ń
    0.08
    ï¼Įåħ¶
    0.08
    ãģĮãģĤãĤĬ
    0.08
    ower
    0.08
     contain
    0.08
    azu
    0.08
    437
    0.08
    Activations Density 0.434%

    No Known Activations