© 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
    5. 50-RESID-POST-GF
    7. 44279
    Prev
    Next
    INDEX
    Explanations

    sorority house square Laboratory actual

    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
    osa
    -0.09
    alen
    -0.08
     kum
    -0.08
     Rosa
    -0.08
    331
    -0.08
    lander
    -0.08
    orgen
    -0.08
    oman
    -0.08
    (s
    -0.08
     Psycho
    -0.08
    POSITIVE LOGITS
    Periph
    0.09
    quette
    0.09
    <|begin_of_text|>
    0.09
    ï¼IJï¼IJ
    0.09
    âĢ³
    0.08
    imax
    0.08
     cutter
    0.08
    ::::::::::
    0.08
    anki
    0.08
    ynos
    0.08
    Activations Density 0.001%

    No Known Activations