© 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
    5. 50-RESID-POST-GF
    7. 44302
    Prev
    Next
    INDEX
    Explanations

    Timba Cubana, bossa nova, scales

    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
     piano
    -0.13
     Piano
    -0.11
     instrumentation
    -0.11
    iano
    -0.10
     Hob
    -0.09
     Beats
    -0.09
     orchest
    -0.09
     beats
    -0.09
     desk
    -0.09
     percussion
    -0.09
    POSITIVE LOGITS
     scales
    0.17
     fret
    0.15
     tast
    0.13
     sol
    0.12
     virt
    0.12
    cales
    0.12
    Impro
    0.11
     solo
    0.11
    reh
    0.11
     scalar
    0.11
    Activations Density 0.016%

    No Known Activations