© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 37456
    Prev
    Next
    INDEX
    Explanations

    article or particle in german and portuguese

    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
     Lingu
    -0.11
     lingu
    -0.11
     vowels
    -0.10
     linguistic
    -0.10
     pronunciation
    -0.10
     gramm
    -0.10
     mont
    -0.09
     uppercase
    -0.09
     Ont
    -0.09
     font
    -0.09
    POSITIVE LOGITS
     ÑģпÑĢÑı
    0.12
     clit
    0.12
    Particle
    0.11
     Particle
    0.11
     dimin
    0.11
     particle
    0.10
    -article
    0.10
    Particles
    0.10
     interrog
    0.10
     decl
    0.10
    Activations Density 0.289%

    No Known Activations