© 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. 37922
    Prev
    Next
    INDEX
    Explanations

    A followed by a concept

    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
     Impl
    -0.10
     Incident
    -0.09
    ament
    -0.09
    ahas
    -0.09
    halb
    -0.08
    omic
    -0.08
     Wich
    -0.08
    flake
    -0.08
     uranus
    -0.08
    erts
    -0.08
    POSITIVE LOGITS
     topic
    0.20
     question
    0.19
     questions
    0.17
     topics
    0.14
    .topic
    0.13
     timely
    0.13
     excellent
    0.12
    topic
    0.12
     pleasure
    0.12
     вопÑĢоÑģ
    0.12
    Activations Density 0.190%

    No Known Activations