© 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. 20405
    Prev
    Next
    INDEX
    Explanations

    blueberries

    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
    otre
    -0.11
     Flower
    -0.10
     barley
    -0.10
     Jade
    -0.10
     prere
    -0.09
     Potato
    -0.09
     èĬ±
    -0.09
     chor
    -0.09
    _salt
    -0.09
     Vegetable
    -0.09
    POSITIVE LOGITS
    berries
    0.31
     berries
    0.29
    berry
    0.29
     Berry
    0.28
     Ber
    0.27
    Berry
    0.26
     Ñıгод
    0.25
     berry
    0.24
    Ber
    0.23
     rasp
    0.23
    Activations Density 0.071%

    No Known Activations