© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 61529
    Prev
    Next
    INDEX
    Explanations

    staying in character

    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
    ãģĬãĤĬ
    -0.11
    addtogroup
    -0.09
    วล
    -0.09
     ï¾Ĭ
    -0.09
     Gale
    -0.09
     ëĮĢíķ´
    -0.09
    âĶĺ
    -0.09
    UpDown
    -0.08
     Dag
    -0.08
     phái
    -0.08
    POSITIVE LOGITS
     true
    0.18
    true
    0.14
     away
    0.14
     focused
    0.13
    away
    0.13
    ed
    0.12
     tuned
    0.12
     True
    0.12
    =true
    0.12
     focus
    0.12
    Activations Density 0.017%

    No Known Activations