© 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
    3. Llama3.3-70B-IT (Instruct)
    5. 50-RESID-POST-GF
    7. 44764
    Prev
    Next
    INDEX
    Explanations

    levels of measurable concepts

    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
    .scalablytyped
    -0.10
    (íģ¬ê¸°
    -0.10
     Peak
    -0.10
    deen
    -0.09
     Gins
    -0.09
     ÐĴлади
    -0.09
     proportions
    -0.09
    ardon
    -0.08
     efficiencies
    -0.08
     Dut
    -0.08
    POSITIVE LOGITS
     levels
    0.47
     level
    0.42
     Levels
    0.33
    levels
    0.33
    Levels
    0.28
    level
    0.27
    _levels
    0.27
     nive
    0.25
     score
    0.25
    æ°´å¹³
    0.24
    Activations Density 0.136%

    No Known Activations