© 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. 38547
    Prev
    Next
    INDEX
    Explanations

    describes features or characteristics

    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
     Chatt
    -0.09
    eker
    -0.09
    ahan
    -0.08
     recharge
    -0.08
    mw
    -0.08
     Mast
    -0.08
    ecure
    -0.08
     doivent
    -0.08
    Jvm
    -0.08
     exactly
    -0.08
    POSITIVE LOGITS
     exc
    0.13
     offer
    0.12
     offers
    0.11
     excel
    0.11
     fares
    0.11
     generally
    0.11
     popularity
    0.11
     relatively
    0.11
     tend
    0.10
     Pros
    0.10
    Activations Density 0.118%

    No Known Activations