© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 41839
    Prev
    Next
    INDEX
    Explanations

    dabei, large corpus, don't, How good

    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
    iso
    -0.10
    iff
    -0.10
    ateway
    -0.10
    imb
    -0.09
    imat
    -0.09
    mary
    -0.09
    irtual
    -0.09
     оÑĤв
    -0.09
     pornstar
    -0.09
    DebugEnabled
    -0.08
    POSITIVE LOGITS
    ually
    0.10
    âĶ¬
    0.09
    SCRIBE
    0.09
    celik
    0.09
    aria
    0.09
    erdem
    0.09
     ue
    0.09
    idges
    0.08
    wide
    0.08
    anked
    0.08
    Activations Density 0.036%

    No Known Activations