Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Llama3.3-70B-IT (Instruct)
    3. 50-RESID-POST-GF
    4. 45002
    Prev
    Next
    INDEX
    Explanations

    argues that

    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
    EMPLARY
    -0.09
     ut
    -0.09
    acci
    -0.09
     sobÄĽ
    -0.08
    eworthy
    -0.08
    or
    -0.08
     exc
    -0.08
    717
    -0.08
     Rab
    -0.08
    901
    -0.08
    POSITIVE LOGITS
     rằng
    0.26
     bahwa
    0.26
     that
    0.19
     dass
    0.16
     ÏĮÏĦι
    0.16
    that
    0.15
     että
    0.15
     hogy
    0.15
     дека
    0.15
     że
    0.14
    Activations Density 0.067%

    No Known Activations