© 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. 43204
    Prev
    Next
    INDEX
    Explanations

    AA.AA.A or AB following AA

    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
    AAAAAAAA
    -0.11
    aaaaaaaa
    -0.11
    LLLL
    -0.10
    llll
    -0.10
    aaaa
    -0.09
    oooooooo
    -0.09
    iiii
    -0.09
    ayi
    -0.09
     Campo
    -0.09
     cof
    -0.09
    POSITIVE LOGITS
     AA
    0.15
    SS
    0.15
    AA
    0.15
    MM
    0.14
    CC
    0.14
     CC
    0.14
     AABB
    0.14
    EE
    0.13
     DD
    0.13
    ABB
    0.13
    Activations Density 0.130%

    No Known Activations