© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 29624
    Prev
    Next
    INDEX
    Explanations

    first-person statements

    np_acts-logits-general · gemini-2.5-flash-lite

    first-person user statements that begin with the pronoun introducing self-focused requests or declarations.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
    -valu
    -0.09
    ¶Į
    -0.09
    aida
    -0.08
     swo
    -0.08
    regon
    -0.08
     weren
    -0.08
    ï¾ļ
    -0.08
    igne
    -0.07
    ë¨
    -0.07
     createStackNavigator
    -0.07
    POSITIVE LOGITS
     recently
    0.13
     need
    0.12
     just
    0.10
    éľĢè¦ģ
    0.10
     Recently
    0.10
     would
    0.10
     Pam
    0.10
    ’;d
    0.10
    æľĢè¿ij
    0.10
    Recently
    0.09
    Activations Density 0.240%

    No Known Activations