© 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. 24570
    Prev
    Next
    INDEX
    Explanations

    Action execution or result

    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
    ï½Ģãĥ½
    -0.09
    /***/
    -0.09
     Ekon
    -0.09
     rám
    -0.08
     ho
    -0.08
     Erg
    -0.08
     ende
    -0.08
     ëĭ¤ìļ´ë°Ľê¸°
    -0.08
    驾
    -0.08
    IColor
    -0.08
    POSITIVE LOGITS
     etc
    0.13
     Action
    0.12
    Action
    0.12
     action
    0.12
    /goto
    0.10
     observation
    0.10
     ActionResult
    0.10
    etc
    0.09
    sip
    0.09
     ACTION
    0.09
    Activations Density 0.034%

    No Known Activations