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. 45040
    Prev
    Next
    INDEX
    Explanations

    items in a list

    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
    ãĢģ​
    -0.11
     âĶľâĶĢâĶĢ
    -0.09
    .gdx
    -0.08
    Fuse
    -0.08
    elon
    -0.08
    sha
    -0.08
    Ñģлов
    -0.08
     baÅŁta
    -0.08
     olup
    -0.08
    ptal
    -0.08
    POSITIVE LOGITS
     and
    0.15
    ãĤĪãģ³
    0.10
    è¿ĺæľī
    0.10
     ìĿ´ëłĩê²Į
    0.09
    and
    0.09
     à¹ģละ
    0.09
    以åıĬ
    0.09
     и
    0.09
     vÃł
    0.09
     Lastly
    0.08
    Activations Density 0.119%

    No Known Activations