© 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. 9191
    Prev
    Next
    INDEX
    Explanations

    magical wishing, called Skinners, next word

    np_acts-logits-general · gemini-2.5-flash-lite

    appositive or definitional phrases that label or name a group or type, often signaled by quotation marks and naming constructions.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
    oyer
    -0.09
    ÑĤÑĢо
    -0.09
    844
    -0.09
    _VO
    -0.08
    estroy
    -0.08
    \tCopyright
    -0.08
     Kurulu
    -0.08
     erst
    -0.08
    UPI
    -0.08
     بÙĩا
    -0.08
    POSITIVE LOGITS
     tzv
    0.09
    agne
    0.09
    ktion
    0.09
    VERRIDE
    0.09
     specials
    0.08
     filetype
    0.08
    Äł
    0.08
     doma
    0.08
     containment
    0.08
     special
    0.08
    Activations Density 0.247%

    No Known Activations