© 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. 31455
    Prev
    Next
    INDEX
    Explanations

    forms of media and entertainment

    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
     music
    -0.24
    /music
    -0.21
     MUSIC
    -0.21
    éŁ³ä¹IJ
    -0.21
     musician
    -0.20
    music
    -0.20
     Music
    -0.20
     musica
    -0.19
     música
    -0.18
    .music
    -0.18
    POSITIVE LOGITS
     dance
    0.15
     lyrics
    0.12
     visuals
    0.12
     spoken
    0.12
     visual
    0.12
     Dance
    0.11
    visual
    0.11
     literature
    0.11
     film
    0.11
    dance
    0.11
    Activations Density 0.034%

    No Known Activations