© 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. 58139
    Prev
    Next
    INDEX
    Explanations

    that/which followed by verbs

    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
     be
    -0.11
     ifndef
    -0.09
     was
    -0.09
    featured
    -0.09
     wasn
    -0.09
     itself
    -0.09
    217
    -0.09
    allas
    -0.09
     fuzz
    -0.09
     باشد
    -0.08
    POSITIVE LOGITS
     are
    0.23
     together
    0.17
     aren
    0.15
     ÙĩستÙĨد
    0.15
     jsou
    0.15
    are
    0.14
    ÑİÑĤÑĮÑģÑı
    0.14
    ä¸Ģèµ·
    0.13
     cum
    0.13
     são
    0.13
    Activations Density 0.103%

    No Known Activations