© 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. 55414
    Prev
    Next
    INDEX
    Explanations

    fireplace and logs

    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
     Cooler
    -0.11
     tents
    -0.11
     cooler
    -0.10
    ebi
    -0.10
     Cooling
    -0.10
    çĽĴ
    -0.09
     Carp
    -0.09
     Coff
    -0.09
    liž
    -0.09
     vip
    -0.09
    POSITIVE LOGITS
     fireplace
    0.33
     fire
    0.26
     Fireplace
    0.25
     hear
    0.24
    çĤī
    0.24
     log
    0.23
     fires
    0.22
     logs
    0.22
     wood
    0.19
    fire
    0.18
    Activations Density 0.049%

    No Known Activations