© 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. 9865
    Prev
    Next
    INDEX
    Explanations

    music video visuals

    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
    -0.18
    éŁ³ä¹IJ
    -0.17
     ìĿĮìķħ
    -0.16
     música
    -0.16
     soundtrack
    -0.16
    éŁ³æ¨Ĥ
    -0.15
     songs
    -0.15
    music
    -0.14
     musician
    -0.14
    éŁ³æ¥½
    -0.14
    POSITIVE LOGITS
     visual
    0.17
     visuals
    0.16
     lip
    0.15
     Visual
    0.14
    Visual
    0.13
    visual
    0.13
     lyrics
    0.13
     chore
    0.13
     visualization
    0.12
     vide
    0.12
    Activations Density 0.055%

    No Known Activations