© 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. 57430
    Prev
    Next
    INDEX
    Explanations

    destination

    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
     Sources
    -0.11
     Sender
    -0.09
    uez
    -0.09
    847
    -0.09
     sources
    -0.09
    _sender
    -0.09
    ä¸ĺ
    -0.09
     upstream
    -0.09
    Sender
    -0.08
     donors
    -0.08
    POSITIVE LOGITS
     destination
    0.71
    destination
    0.55
     Destination
    0.50
     destinations
    0.49
     target
    0.47
    Destination
    0.46
    (destination
    0.39
     destino
    0.38
    _destination
    0.38
    缮æłĩ
    0.36
    Activations Density 0.135%

    No Known Activations