© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 33897
    Prev
    Next
    INDEX
    Explanations

    a single item

    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
    лки
    -0.09
    938
    -0.09
     denomin
    -0.09
    ¶Į
    -0.09
    uze
    -0.09
    inand
    -0.09
    .sax
    -0.08
     din
    -0.08
    ddy
    -0.08
    postalcode
    -0.08
    POSITIVE LOGITS
     individual
    0.12
     einzel
    0.11
     item
    0.11
     pair
    0.10
    411
    0.10
    item
    0.09
     ones
    0.09
     Individual
    0.09
    441
    0.09
     indice
    0.08
    Activations Density 0.283%

    No Known Activations