© 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. 34434
    Prev
    Next
    INDEX
    Explanations

    pas followed by os or French negation

    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
    eh
    -0.10
    uff
    -0.10
    tras
    -0.10
    pine
    -0.10
    hem
    -0.10
    eted
    -0.09
    helm
    -0.09
    ÂŃi
    -0.09
    tring
    -0.09
    pector
    -0.09
    POSITIVE LOGITS
    sthrough
    0.19
    adena
    0.15
    ible
    0.13
    ively
    0.12
    ionate
    0.12
    sth
    0.12
    SED
    0.12
    engers
    0.11
    enger
    0.11
    ION
    0.11
    Activations Density 0.015%

    No Known Activations