© 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. 64431
    Prev
    Next
    INDEX
    Explanations

    how things relate

    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
    chen
    -0.09
     Franz
    -0.09
    ायन
    -0.09
     Kul
    -0.09
    odb
    -0.08
     Invent
    -0.08
    екÑĥ
    -0.08
     advent
    -0.08
     Maxwell
    -0.08
    olo
    -0.08
    POSITIVE LOGITS
     golden
    0.17
     Golden
    0.15
    æ¯Ķä¾ĭ
    0.15
    Golden
    0.14
     rule
    0.14
     grid
    0.13
    golden
    0.13
     Grid
    0.13
     ratio
    0.13
     module
    0.12
    Activations Density 0.061%

    No Known Activations