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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Llama3.3-70B-IT (Instruct)
    3. 50-RESID-POST-GF
    4. 44912
    Prev
    Next
    INDEX
    Explanations

    extensive scope

    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
    erge
    -0.11
    subs
    -0.10
    TextWriter
    -0.09
    seg
    -0.09
    535
    -0.09
    ipl
    -0.09
    inger
    -0.08
    ysz
    -0.08
    ESIS
    -0.08
    rink
    -0.08
    POSITIVE LOGITS
     amounts
    0.18
    ively
    0.15
    /ext
    0.15
    amount
    0.14
     amount
    0.14
     Amount
    0.13
    ions
    0.11
     knowledge
    0.11
    -reaching
    0.10
    ley
    0.10
    Activations Density 0.021%

    No Known Activations