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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Llama3.3-70B-IT
    3. 50-RESID-POST-GF
    4. 43839
    Prev
    Next
    INDEX
    Explanations

    user assistant

    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
    om
    -0.09
    chnitt
    -0.09
     Qi
    -0.09
    ìĪľ
    -0.09
     Fu
    -0.08
     Blind
    -0.08
    oning
    -0.08
    illon
    -0.08
    s
    -0.08
     reasons
    -0.08
    POSITIVE LOGITS
     ready
    0.14
     please
    0.13
    please
    0.11
    Please
    0.11
    请
    0.11
     гоÑĤов
    0.11
     now
    0.11
     hãy
    0.11
    ready
    0.11
     READY
    0.11
    Activations Density 0.122%

    No Known Activations