© 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. 25053
    Prev
    Next
    INDEX
    Explanations

    a boolean explanation

    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
     conson
    -0.11
     Explicit
    -0.10
    abcdefghijkl
    -0.10
    çĶ·æĢ§
    -0.09
    SSIP
    -0.09
     ç¿
    -0.09
    Ðĭ
    -0.08
     translated
    -0.08
    ãĤ¹ãĤ¿ãĥ¼
    -0.08
    explicit
    -0.08
    POSITIVE LOGITS
     relative
    0.16
     context
    0.15
    relative
    0.13
     Relative
    0.12
    .context
    0.11
    (context
    0.11
     contexts
    0.11
     rel
    0.11
     nit
    0.11
     ped
    0.11
    Activations Density 0.207%

    No Known Activations