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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 33679
    Prev
    Next
    INDEX
    Explanations

    good and evil, control, morality, age

    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
    çĶ¨äºİ
    -0.10
     because
    -0.09
     moments
    -0.09
    odyn
    -0.09
     Bat
    -0.09
     WHATSOEVER
    -0.08
     vi
    -0.08
    tractor
    -0.08
    nip
    -0.08
    ller
    -0.08
    POSITIVE LOGITS
     told
    0.15
     tema
    0.10
    themes
    0.10
     بط
    0.10
    é¡Į
    0.09
     angle
    0.09
     Abyss
    0.09
     Thema
    0.08
    casting
    0.08
     cou
    0.08
    Activations Density 0.120%

    No Known Activations