© 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. 26760
    Prev
    Next
    INDEX
    Explanations

    TensorFlow, PyTorch, Caffe

    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
    -FIRST
    -0.11
    hamster
    -0.10
     knot
    -0.10
    iffies
    -0.10
     tam
    -0.09
    éĹ²
    -0.09
     Disposable
    -0.09
     Sez
    -0.09
     knots
    -0.09
    krom
    -0.09
    POSITIVE LOGITS
     Rapids
    0.14
     cud
    0.14
     rap
    0.14
     Trit
    0.13
     cu
    0.13
    cu
    0.13
     Amp
    0.13
    caffe
    0.13
     inference
    0.13
    Asc
    0.12
    Activations Density 0.072%

    No Known Activations