© 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
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 35457
    Prev
    Next
    INDEX
    Explanations

    story elements and characters

    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
     stories
    -0.18
    stories
    -0.16
     Stories
    -0.15
    Stories
    -0.15
     storyline
    -0.14
     tales
    -0.14
    æķħäºĭ
    -0.13
     storytelling
    -0.12
     narratives
    -0.11
     story
    -0.11
    POSITIVE LOGITS
     dialogue
    0.22
     dialog
    0.21
     plot
    0.19
     character
    0.18
     Dialog
    0.18
     characters
    0.18
     Dialogue
    0.17
    plot
    0.16
     Plot
    0.16
     dialogs
    0.15
    Activations Density 0.157%

    No Known Activations