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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Llama3.3-70B-IT (Instruct)
    3. 50-RESID-POST-GF
    4. 44933
    Prev
    Next
    INDEX
    Explanations

    I'm sorry, unfortunately

    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
     Yup
    -0.10
     prob
    -0.10
     Archer
    -0.09
     already
    -0.09
     after
    -0.09
    _
    -0.09
    cest
    -0.09
     Yue
    -0.09
     when
    -0.09
    ique
    -0.09
    POSITIVE LOGITS
     unable
    0.16
    Unfortunately
    0.16
     sorry
    0.16
    çͱäºİ
    0.15
    Sorry
    0.15
    SOR
    0.15
     Sorry
    0.15
    æĹłæ³ķ
    0.15
    sorry
    0.14
     Unfortunately
    0.13
    Activations Density 0.230%

    No Known Activations