© 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. 3937
    Prev
    Next
    INDEX
    Explanations

    feeling and familiarity

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

    sentence starts and response-openers in assistant messages, marked by double newlines and adjacent punctuation (commas, periods, question marks).

    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
    //{{
    -0.11
     boredom
    -0.10
    APO
    -0.09
     regret
    -0.09
     sadness
    -0.09
    íĿ¥
    -0.09
    tainment
    -0.08
     everything
    -0.08
     spec
    -0.08
    _iterator
    -0.08
    POSITIVE LOGITS
     familiar
    0.19
     familiarity
    0.15
     sympath
    0.14
     Fam
    0.14
     syndrome
    0.13
     feeling
    0.12
     struggle
    0.12
     scenario
    0.12
     sympathy
    0.12
    amiliar
    0.12
    Activations Density 0.195%

    No Known Activations