© 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 (Instruct)
    5. 50-RESID-POST-GF
    7. 44712
    Prev
    Next
    INDEX
    Explanations

    then followed by action

    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
    EMPLARY
    -0.10
    errat
    -0.09
     завиÑģим
    -0.08
    abee
    -0.08
    ucci
    -0.08
    roof
    -0.08
    ifle
    -0.08
    ॰
    -0.08
    çĵľ
    -0.08
    uft
    -0.08
    POSITIVE LOGITS
     answer
    0.15
     finally
    0.13
     provide
    0.13
    answer
    0.12
     give
    0.11
     answers
    0.11
     based
    0.11
     tell
    0.11
     offer
    0.11
     Answer
    0.10
    Activations Density 0.194%

    No Known Activations