© 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
    5. 50-RESID-POST-GF
    7. 33887
    Prev
    Next
    INDEX
    Explanations

    "[your answer]" when a condition

    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
    seealso
    -0.09
     :\n\n\n\n
    -0.09
     Orchard
    -0.09
    afa
    -0.09
    /******/
    -0.08
    ActionCreators
    -0.08
    918
    -0.08
     misd
    -0.08
    pressor
    -0.08
    za
    -0.08
    POSITIVE LOGITS
    s
    0.14
     Counts
    0.09
    евид
    0.09
     Reverse
    0.09
    [::-
    0.08
    aira
    0.08
    ych
    0.08
     canned
    0.08
     Starr
    0.08
     MVP
    0.08
    Activations Density 0.018%

    No Known Activations