© 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. 34072
    Prev
    Next
    INDEX
    Explanations

    mental health conditions and personality

    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
     paranoid
    -0.10
     unp
    -0.10
     productive
    -0.09
     suicidal
    -0.09
     CLR
    -0.09
     psychology
    -0.09
     potentially
    -0.09
     paranoia
    -0.08
     Psychology
    -0.08
     relations
    -0.08
    POSITIVE LOGITS
     perfection
    0.16
     underlying
    0.13
     personality
    0.13
     lack
    0.13
     upbringing
    0.12
     low
    0.12
    ogi
    0.12
     histories
    0.11
     Personality
    0.11
     personalities
    0.11
    Activations Density 0.085%

    No Known Activations