© 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. 20844
    Prev
    Next
    INDEX
    Explanations

    noun followed by its role/type

    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
     consort
    -0.09
    Explorer
    -0.09
     proceedings
    -0.08
     Hanna
    -0.08
    yla
    -0.08
     pathways
    -0.08
    ãģ¨ãģĦãģĨ
    -0.08
    ÑģÑĤÑĮ
    -0.08
     actionTypes
    -0.08
    obbies
    -0.08
    POSITIVE LOGITS
     tool
    0.19
     option
    0.18
     resource
    0.15
     asset
    0.15
     source
    0.15
    tool
    0.14
     item
    0.14
     device
    0.13
     destination
    0.13
     vehicle
    0.13
    Activations Density 0.143%

    No Known Activations