© 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. 56864
    Prev
    Next
    INDEX
    Explanations

    use and other actions

    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
     usage
    -0.15
    \tusage
    -0.11
    -used
    -0.10
     kullanılır
    -0.10
    _usage
    -0.10
     using
    -0.09
    /use
    -0.09
    ä¿
    -0.09
     Usage
    -0.09
    ucket
    -0.09
    POSITIVE LOGITS
     abuse
    0.18
     Abuse
    0.18
     abuses
    0.13
     abused
    0.13
     abusing
    0.12
     misuse
    0.12
    abus
    0.10
     sale
    0.10
    coil
    0.09
     HttpHeaders
    0.09
    Activations Density 0.052%

    No Known Activations