© 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
    2. Llama3.3-70B-IT (Instruct)
    3. 50-RESID-POST-GF
    4. 34039
    Prev
    Next
    INDEX
    Explanations

    routine patrol suspicious activity

    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
     lunch
    -0.33
     Lunch
    -0.29
     afternoon
    -0.26
     noon
    -0.25
     lunches
    -0.22
     Noon
    -0.21
    noon
    -0.19
     sunshine
    -0.17
     sunny
    -0.17
     sunlight
    -0.16
    POSITIVE LOGITS
     midnight
    0.32
     night
    0.30
    å¤ľ
    0.30
     noct
    0.28
     Night
    0.27
     ноÑĩ
    0.26
    Night
    0.26
    -night
    0.25
    night
    0.24
     late
    0.24
    Activations Density 0.167%

    No Known Activations