© 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. 37171
    Prev
    Next
    INDEX
    Explanations

    sequence of numbers

    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
    ABCDEFGHI
    -0.13
    abcdefghijklmnop
    -0.13
    ABCDEFGHIJKLMNOP
    -0.13
    abcdefghijkl
    -0.12
    ABCDEFG
    -0.11
     Alb
    -0.10
    oot
    -0.10
    --
    -0.09
     Marion
    -0.09
    IBE
    -0.09
    POSITIVE LOGITS
    123
    0.20
    789
    0.18
    876
    0.17
    456
    0.17
    321
    0.16
    345
    0.15
    987
    0.15
    234
    0.14
    erty
    0.13
    poi
    0.13
    Activations Density 0.060%

    No Known Activations