© 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. 44387
    Prev
    Next
    INDEX
    Explanations

    enter input

    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
    chez
    -0.09
     Gul
    -0.09
    ãĢĢãĢĢ
    -0.08
    igel
    -0.08
     Lamb
    -0.08
    orgot
    -0.08
    endas
    -0.08
    askan
    -0.08
     Fehler
    -0.08
    errer
    -0.08
    POSITIVE LOGITS
     input
    0.39
     entered
    0.33
     inputs
    0.31
    è¾ĵåħ¥
    0.30
    input
    0.28
     Input
    0.27
     Entered
    0.25
     ìŀħëł¥
    0.25
     userInput
    0.25
    entered
    0.24
    Activations Density 0.158%

    No Known Activations