© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 35816
    Prev
    Next
    INDEX
    Explanations

    help or guidance

    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
    orum
    -0.09
     indirectly
    -0.09
    utin
    -0.08
    /ca
    -0.08
    -ca
    -0.08
    aginator
    -0.08
    gle
    -0.08
    kuk
    -0.08
     huy
    -0.08
     elect
    -0.08
    POSITIVE LOGITS
     walk
    0.37
     guide
    0.35
     walked
    0.32
    walk
    0.30
     walks
    0.30
     guides
    0.30
    Walk
    0.29
     Walk
    0.29
    guide
    0.27
    Guide
    0.24
    Activations Density 0.269%

    No Known Activations