© 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. 58095
    Prev
    Next
    INDEX
    Explanations

    fondness, interest, curiosity

    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
     appet
    -0.09
     hunger
    -0.09
     Tencent
    -0.09
     craving
    -0.09
     thirst
    -0.09
     thirsty
    -0.09
     adamant
    -0.09
    rog
    -0.08
     intox
    -0.08
    615
    -0.08
    POSITIVE LOGITS
     partial
    0.25
     fond
    0.24
     Fond
    0.20
     into
    0.16
     interested
    0.16
    partial
    0.16
     Partial
    0.16
     fan
    0.15
     fon
    0.15
     fans
    0.15
    Activations Density 0.109%

    No Known Activations