Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Llama3.3-70B-IT (Instruct)
    3. 50-RESID-POST-GF
    4. 38436
    Prev
    Next
    INDEX
    Explanations

    Earth is flat

    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
    ÐĴÑĤ
    -0.09
    ,readonly
    -0.09
    ToPoint
    -0.08
     ÙĩÙħاÙĨ
    -0.08
    irth
    -0.08
     Ñģамого
    -0.07
     ifndef
    -0.07
    oga
    -0.07
    olon
    -0.07
     acquaint
    -0.07
    POSITIVE LOGITS
     this
    0.11
     these
    0.10
    å¦ĤæŃ¤
    0.10
     ÚĨÙĨÛĮÙĨ
    0.09
     böyle
    0.09
    ï¼īãģ¯
    0.09
    this
    0.08
     tÃŃmto
    0.08
    these
    0.08
    è¿Ļæł·
    0.08
    Activations Density 0.111%

    No Known Activations