© 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. 31988
    Prev
    Next
    INDEX
    Explanations

    ение /-ениÑı endings

    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
    ÑıÑīиÑħ
    -0.11
    iness
    -0.10
     precious
    -0.09
     Santana
    -0.09
    иÑĤелÑĮÑģÑĤва
    -0.09
     offsets
    -0.09
    icken
    -0.09
    osto
    -0.09
    olis
    -0.09
    yd
    -0.09
    POSITIVE LOGITS
    ение
    0.20
    ениÑı
    0.14
    ible
    0.10
    enie
    0.10
    eno
    0.10
    aleur
    0.10
     Brent
    0.09
     consenting
    0.09
    enia
    0.09
    ened
    0.09
    Activations Density 0.099%

    No Known Activations