© 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. 62374
    Prev
    Next
    INDEX
    Explanations

    starting and end points

    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
     cords
    -0.12
     paths
    -0.11
     Paths
    -0.11
    Tracks
    -0.11
    tracks
    -0.11
    Paths
    -0.11
     targetType
    -0.10
     cables
    -0.10
     Tracks
    -0.10
    dik
    -0.10
    POSITIVE LOGITS
     end
    0.35
     ends
    0.35
     Ends
    0.25
    端
    0.24
    æľ«
    0.23
     конÑĨа
    0.22
     endpoint
    0.22
    -end
    0.22
     ended
    0.21
     tip
    0.21
    Activations Density 0.117%

    No Known Activations