Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Llama3.3-70B-IT (Instruct)
    3. 50-RESID-POST-GF
    4. 34283
    Prev
    Next
    INDEX
    Explanations

    ap, apostrophes, aprr

    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
     recre
    -0.09
    ional
    -0.09
    pur
    -0.09
    ionale
    -0.09
     Yuk
    -0.09
     ADM
    -0.09
    mand
    -0.09
    ï½§
    -0.08
    ilitation
    -0.08
    press
    -0.08
    POSITIVE LOGITS
    (AP
    0.16
     ap
    0.15
     Ap
    0.14
    (ap
    0.13
    .Ap
    0.13
     ап
    0.13
     dụng
    0.12
    aches
    0.12
    ause
    0.11
    trinsic
    0.11
    Activations Density 0.061%

    No Known Activations