© 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. 40288
    Prev
    Next
    INDEX
    Explanations

    orchestra symphony conductor

    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
     guitar
    -0.17
     Guitar
    -0.16
    åĶ±
    -0.14
    _song
    -0.13
     songs
    -0.13
     songwriter
    -0.12
     singing
    -0.12
     flute
    -0.12
     song
    -0.12
     Choir
    -0.11
    POSITIVE LOGITS
     sym
    0.23
     conduct
    0.21
     conducted
    0.21
     conductor
    0.19
     Conduct
    0.19
    sym
    0.19
     chamber
    0.18
     Sym
    0.18
    Sym
    0.18
     conducting
    0.18
    Activations Density 0.046%

    No Known Activations