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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Llama3.3-70B-IT (Instruct)
    3. 50-RESID-POST-GF
    4. 65498
    Prev
    Next
    INDEX
    Explanations

    material

    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
    yor
    -0.11
    exe
    -0.11
    Ðĭ
    -0.11
    annis
    -0.10
    eson
    -0.10
    isÃŃ
    -0.10
    tright
    -0.09
    778
    -0.09
    ear
    -0.09
    à¤ľà¤¹
    -0.09
    POSITIVE LOGITS
    ity
    0.28
    istic
    0.27
    ized
    0.23
    ization
    0.20
    izing
    0.19
    ize
    0.19
    led
    0.19
    istically
    0.18
    izes
    0.17
    ism
    0.16
    Activations Density 0.023%

    No Known Activations