© 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. 44402
    Prev
    Next
    INDEX
    Explanations

    chemicals and compounds

    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
     cud
    -0.11
     oxy
    -0.10
    adge
    -0.10
     oxide
    -0.09
    lea
    -0.09
    oxid
    -0.09
     toxin
    -0.09
    rites
    -0.08
    annels
    -0.08
    skirts
    -0.08
    POSITIVE LOGITS
     chemicals
    0.36
     chemical
    0.25
     Chemical
    0.20
    chemical
    0.19
     industrial
    0.18
     substances
    0.17
     materials
    0.17
     substance
    0.16
     chemistry
    0.15
     compounds
    0.15
    Activations Density 0.112%

    No Known Activations