© 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. 22649
    Prev
    Next
    INDEX
    Explanations

    engagement and retention

    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
     responsiveness
    -0.13
     strength
    -0.11
     substr
    -0.10
    strength
    -0.10
     Hansen
    -0.10
     Consort
    -0.10
     flush
    -0.10
     Lac
    -0.09
     stability
    -0.09
     Stability
    -0.09
    POSITIVE LOGITS
     engagement
    0.25
     satisfaction
    0.25
     Engagement
    0.21
     Satisfaction
    0.20
    atisfaction
    0.18
     Ñĥдов
    0.17
    _eng
    0.15
     retention
    0.15
     вов
    0.15
     задов
    0.14
    Activations Density 0.074%

    No Known Activations