© 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. 46849
    Prev
    Next
    INDEX
    Explanations

    noun-forming suffixes

    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
     italiana
    -0.12
    urette
    -0.11
    érica
    -0.11
     ÑĤакаÑı
    -0.11
    strup
    -0.11
    ÑĪла
    -0.11
    /stdc
    -0.11
     españ
    -0.11
    ovna
    -0.11
    icina
    -0.10
    POSITIVE LOGITS
    ismo
    0.20
    amento
    0.16
    amiento
    0.16
    isme
    0.15
    imento
    0.14
    ascimento
    0.13
    ito
    0.13
    olvimento
    0.13
    imiento
    0.12
    ancement
    0.12
    Activations Density 0.257%

    No Known Activations