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. 65301
    Prev
    Next
    INDEX
    Explanations

    the west university world horror

    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
     Cyr
    -0.11
     Napoleon
    -0.10
     romant
    -0.10
     poetic
    -0.10
     Nap
    -0.09
     Disney
    -0.09
     anonym
    -0.09
     Drew
    -0.09
    indo
    -0.09
    storybook
    -0.09
    POSITIVE LOGITS
     Joyce
    0.19
     novel
    0.17
     Nobel
    0.17
     Hem
    0.15
     Yok
    0.15
    Mailer
    0.14
     novels
    0.14
    Joy
    0.13
     experimental
    0.13
    nov
    0.13
    Activations Density 0.075%

    No Known Activations