© 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. 30673
    Prev
    Next
    INDEX
    Explanations

    goal based

    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
    734
    -0.10
    udp
    -0.09
    ette
    -0.09
     Yao
    -0.09
    ottes
    -0.09
    ous
    -0.09
     Berk
    -0.09
    alore
    -0.09
    ity
    -0.09
    oft
    -0.08
    POSITIVE LOGITS
    posts
    0.19
    keepers
    0.19
    imate
    0.14
    post
    0.13
    ÙħÙĨد
    0.13
    keeping
    0.12
     Getter
    0.12
    getter
    0.11
    /Object
    0.11
    mouth
    0.11
    Activations Density 0.036%

    No Known Activations