© 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. 34731
    Prev
    Next
    INDEX
    Explanations

    channel send message

    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
     gib
    -0.10
    acci
    -0.10
     Hut
    -0.09
    erras
    -0.09
     Wand
    -0.09
     Pascal
    -0.09
    iske
    -0.08
     drib
    -0.08
    eus
    -0.08
     prere
    -0.08
    POSITIVE LOGITS
     channel
    0.29
    channel
    0.23
     Channel
    0.22
     channels
    0.22
    Channel
    0.20
    -channel
    0.19
    .channel
    0.18
    (channel
    0.17
     Channels
    0.17
    _channel
    0.17
    Activations Density 0.034%

    No Known Activations