© 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. 18005
    Prev
    Next
    INDEX
    Explanations

    certificate, filename, price, costs, lengths, goals, declare, name

    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
    FRING
    -0.08
    (END
    -0.08
    flater
    -0.08
    UNUSED
    -0.08
    ebek
    -0.08
     ragaz
    -0.08
    ï¿
    -0.08
     nastav
    -0.07
     Antworten
    -0.07
    #ac
    -0.07
    POSITIVE LOGITS
     Allan
    0.08
     obviously
    0.08
    _bw
    0.07
     Herc
    0.07
     its
    0.07
     âĢ¦
    0.07
    514
    0.07
    اسÙĩ
    0.07
     Ins
    0.07
    å¯
    0.07
    Activations Density 1.008%

    No Known Activations