© 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. 34613
    Prev
    Next
    INDEX
    Explanations

    carbon dioxide, carbon, sodium carbonate, exchange

    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
     Nina
    -0.10
    bris
    -0.09
    åº
    -0.09
     celib
    -0.09
     Gener
    -0.09
    _pod
    -0.09
    andez
    -0.09
    ucas
    -0.08
     Celt
    -0.08
    porte
    -0.08
    POSITIVE LOGITS
     CO
    0.40
     carbon
    0.37
     Carbon
    0.33
    CO
    0.33
    Carbon
    0.29
    carbon
    0.28
    .CO
    0.23
    _CO
    0.22
     carbonate
    0.19
    arbon
    0.18
    Activations Density 0.039%

    No Known Activations