© 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. 42394
    Prev
    Next
    INDEX
    Explanations

    soft spot

    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
     Prescott
    -0.09
     forfe
    -0.09
     rarity
    -0.09
    /libs
    -0.08
    hurst
    -0.08
     Observer
    -0.08
     intros
    -0.08
     Hut
    -0.08
     Pamela
    -0.08
     Fam
    -0.08
    POSITIVE LOGITS
     fond
    0.29
     weakness
    0.27
     affinity
    0.22
     Fond
    0.22
     partial
    0.21
     preference
    0.18
     appreciation
    0.18
     passion
    0.18
     interest
    0.18
     Weak
    0.17
    Activations Density 0.104%

    No Known Activations