© 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. 58201
    Prev
    Next
    INDEX
    Explanations

    proposed plan or job service

    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
     baiser
    -0.21
     nouve
    -0.21
     célib
    -0.18
     meille
    -0.15
     gratuits
    -0.15
     rencont
    -0.14
     gratuitement
    -0.13
     sécur
    -0.13
     gratuites
    -0.13
     nouvel
    -0.12
    POSITIVE LOGITS
     «
    0.18
     negoci
    0.17
     exemple
    0.16
    «
    0.14
    _bloc
    0.14
     :\n
    0.14
     fonction
    0.14
    _proba
    0.14
    _infos
    0.14
     notably
    0.14
    Activations Density 0.517%

    No Known Activations