© 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. 40824
    Prev
    Next
    INDEX
    Explanations

    song or single

    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
     lyric
    -0.12
     Musical
    -0.11
     lyr
    -0.11
    Series
    -0.10
     musical
    -0.09
     Series
    -0.09
     Singer
    -0.09
    ControlEvents
    -0.09
     books
    -0.09
    jure
    -0.09
    POSITIVE LOGITS
     song
    0.42
     track
    0.40
     tracks
    0.32
    track
    0.30
     songs
    0.29
    song
    0.29
    -track
    0.27
     пеÑģ
    0.26
    æĽ²
    0.26
    Track
    0.25
    Activations Density 0.066%

    No Known Activations