© 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. 44383
    Prev
    Next
    INDEX
    Explanations

    when followed by 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
    eler
    -0.09
     unchanged
    -0.09
    vens
    -0.09
    uele
    -0.09
     Bent
    -0.09
    rix
    -0.09
    unner
    -0.09
     nikdy
    -0.09
    381
    -0.09
    edl
    -0.08
    POSITIVE LOGITS
     finally
    0.17
     least
    0.17
     Least
    0.14
     comes
    0.13
    least
    0.12
     becomes
    0.12
    finally
    0.12
     become
    0.11
     inev
    0.11
     Finally
    0.11
    Activations Density 0.134%

    No Known Activations