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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT (Instruct)
    5. 50-RESID-POST-GF
    7. 38521
    Prev
    Next
    INDEX
    Explanations

    new musical forms and styles

    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
     flute
    -0.13
     Vocal
    -0.12
     rhyth
    -0.11
    çĽijåIJ¬é¡µéĿ¢
    -0.10
     chant
    -0.10
     acoustic
    -0.10
     beacon
    -0.09
    utable
    -0.09
     clocks
    -0.09
     mir
    -0.09
    POSITIVE LOGITS
     notes
    0.33
    notes
    0.27
     note
    0.25
     Notes
    0.23
     discord
    0.23
    -notes
    0.22
    Notes
    0.22
     NOTES
    0.21
     notas
    0.21
     pitch
    0.19
    Activations Density 0.097%

    No Known Activations