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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Llama3.3-70B-IT (Instruct)
    3. 50-RESID-POST-GF
    4. 65527
    Prev
    Next
    INDEX
    Explanations

    experiencing emotions and states

    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
    _experience
    -0.10
    EEP
    -0.09
    ilion
    -0.09
    ispecies
    -0.09
    ì§ĵ
    -0.08
    esson
    -0.08
    ä»
    -0.08
    ieu
    -0.08
     experi
    -0.08
    azi
    -0.08
    POSITIVE LOGITS
    à¸ģารà¸ĵ
    0.11
    /end
    0.10
    ably
    0.10
    /k
    0.10
    uality
    0.10
    ually
    0.09
    ophon
    0.09
    entially
    0.09
    ible
    0.09
    imen
    0.09
    Activations Density 0.018%

    No Known Activations