© 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. 44756
    Prev
    Next
    INDEX
    Explanations

    app and device broadcasting

    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
    byss
    -0.09
     PIXEL
    -0.09
     competitive
    -0.09
     polygon
    -0.09
     input
    -0.09
     Lon
    -0.08
    omain
    -0.08
    ãĤĽ
    -0.08
     Telegraph
    -0.08
    ibar
    -0.08
    POSITIVE LOGITS
     peer
    0.30
     Peer
    0.27
    Peer
    0.24
    peer
    0.24
     peers
    0.21
     Nap
    0.18
    -peer
    0.16
    (peer
    0.16
    _peer
    0.15
     rendez
    0.14
    Activations Density 0.039%

    No Known Activations