© 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. 37956
    Prev
    Next
    INDEX
    Explanations

    phone not charging issue

    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
    ä¹Ĥ
    -0.08
    zh
    -0.08
    asion
    -0.08
     animated
    -0.08
    roti
    -0.08
     pulled
    -0.08
     dust
    -0.08
    anni
    -0.08
    _EXCEPTION
    -0.08
     Wheat
    -0.08
    POSITIVE LOGITS
     Unable
    0.13
    udden
    0.13
     suddenly
    0.13
     unable
    0.12
     inability
    0.12
    æĹłæ³ķ
    0.12
    Unable
    0.11
     won
    0.11
     sudden
    0.11
    won
    0.11
    Activations Density 0.200%

    No Known Activations