© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Llama3.3-70B-IT
    3. 50-RESID-POST-GF
    4. 33912
    Prev
    Next
    INDEX
    Explanations

    should not tolerate

    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
     Ñģом
    -0.10
    raid
    -0.09
    oux
    -0.09
    immel
    -0.09
    wand
    -0.09
     Retorna
    -0.09
    agate
    -0.09
    antom
    -0.09
     STILL
    -0.08
    Wunused
    -0.08
    POSITIVE LOGITS
     unacceptable
    0.23
    acceptable
    0.17
     toler
    0.16
     acceptable
    0.16
     cannot
    0.16
    tol
    0.16
     intoler
    0.15
     absolutely
    0.15
     tolerance
    0.14
    olerance
    0.13
    Activations Density 0.078%

    No Known Activations