© 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. 34098
    Prev
    Next
    INDEX
    Explanations

    and it

    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
    inite
    -0.10
    ague
    -0.09
    566
    -0.09
    ichert
    -0.09
    ittel
    -0.09
     consequently
    -0.09
    ToolTip
    -0.08
    را
    -0.08
    èĵ
    -0.08
     бÑĭ
    -0.08
    POSITIVE LOGITS
     it
    0.22
    å®ĥ
    0.17
     nó
    0.17
     оно
    0.14
    ãģĿãĤĮãģ¯
    0.12
     It
    0.12
    rog
    0.12
    /or
    0.12
    ï¼Įå®ĥ
    0.11
    it
    0.11
    Activations Density 0.088%

    No Known Activations