© 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. 61997
    Prev
    Next
    INDEX
    Explanations

    properties describing materials

    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
    fully
    -0.10
     ï½°
    -0.09
     sexes
    -0.09
    /ex
    -0.09
    roit
    -0.09
     antioxidants
    -0.09
    ovu
    -0.09
    ously
    -0.08
    actively
    -0.08
     emot
    -0.08
    POSITIVE LOGITS
     material
    0.22
     substance
    0.20
     materials
    0.19
    ity
    0.18
     substances
    0.16
    ITY
    0.16
    material
    0.15
     agents
    0.15
    materials
    0.14
     маÑĤеÑĢиал
    0.14
    Activations Density 0.076%

    No Known Activations