© 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. 4080
    Prev
    Next
    INDEX
    Explanations

    many technical terms

    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
     adjective
    -0.12
     spelling
    -0.10
    .idea
    -0.10
     synonym
    -0.09
    328
    -0.08
    ıi
    -0.08
     surname
    -0.08
    adic
    -0.08
     pronunciation
    -0.08
    èĪį
    -0.08
    POSITIVE LOGITS
     terms
    0.36
     technical
    0.32
    terms
    0.28
     Terms
    0.27
     j
    0.26
    æľ¯
    0.26
    Terms
    0.26
     termin
    0.26
    technical
    0.25
    termin
    0.25
    Activations Density 0.312%

    No Known Activations