© 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. 34789
    Prev
    Next
    INDEX
    Explanations

    a tempo of

    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
     harmon
    -0.15
     Harmon
    -0.10
     bandwidth
    -0.09
     harmonic
    -0.09
     recess
    -0.09
     Voice
    -0.09
     melodies
    -0.09
    DataTable
    -0.09
     conc
    -0.09
    ALCHEMY
    -0.09
    POSITIVE LOGITS
     beat
    0.21
    æĭį
    0.19
    beat
    0.17
     beats
    0.16
     measure
    0.16
     Beat
    0.15
    Beat
    0.14
    empo
    0.14
     met
    0.14
     measures
    0.14
    Activations Density 0.035%

    No Known Activations