© 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. 34471
    Prev
    Next
    INDEX
    Explanations

    fiction theory

    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
    497
    -0.10
     empir
    -0.10
    adero
    -0.09
    _topics
    -0.09
    illa
    -0.09
     pragmatic
    -0.08
    irá
    -0.08
     Whisper
    -0.08
    (HWND
    -0.08
    419
    -0.08
    POSITIVE LOGITS
     theory
    0.41
    çIJĨ论
    0.38
     theoretical
    0.37
     abstract
    0.35
     ÑĤеоÑĢ
    0.35
    theory
    0.33
     Theory
    0.32
     theoret
    0.32
     THEORY
    0.32
    Theory
    0.29
    Activations Density 0.219%

    No Known Activations