© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 62397
    Prev
    Next
    INDEX
    Explanations

    tells the story of

    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
     originals
    -0.08
    .dtd
    -0.08
    _imag
    -0.08
    >(()
    -0.08
     memorable
    -0.08
     fun
    -0.08
     Characters
    -0.08
    ety
    -0.08
    [js
    -0.08
    vangst
    -0.08
    POSITIVE LOGITS
     story
    0.68
    story
    0.47
     Story
    0.45
     stories
    0.45
    æķħäºĭ
    0.44
     tale
    0.43
     STORY
    0.43
    Story
    0.41
    -story
    0.39
    .story
    0.36
    Activations Density 0.157%

    No Known Activations