© 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. 56453
    Prev
    Next
    INDEX
    Explanations

    referring to names or 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
    StandardItem
    -0.10
     COPYING
    -0.09
     声
    -0.09
    éĢģæĸĻ
    -0.08
    ãĢĢï¾Ĭ
    -0.08
    htdocs
    -0.08
     ULONG
    -0.08
     maduras
    -0.08
     excer
    -0.08
     å¾ĴæŃ©
    -0.08
    POSITIVE LOGITS
     term
    0.29
     name
    0.28
    term
    0.23
     refer
    0.21
    name
    0.21
    ì¹Ń
    0.20
     referring
    0.20
    åIJį称
    0.20
    ronym
    0.20
     nickname
    0.19
    Activations Density 0.819%

    No Known Activations