© 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. 40821
    Prev
    Next
    INDEX
    Explanations

    in positions

    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
     Shrine
    -0.09
    .localScale
    -0.09
     directional
    -0.09
    å§ĵ
    -0.09
    961
    -0.09
    ymes
    -0.09
     Lesb
    -0.08
    acz
    -0.08
    ientes
    -0.08
    éŁ
    -0.08
    POSITIVE LOGITS
     position
    0.59
     positions
    0.46
    position
    0.45
     Position
    0.40
    .position
    0.38
     пози
    0.38
     vá»ĭ
    0.38
     posición
    0.38
    Position
    0.37
    ä½įç½®
    0.37
    Activations Density 0.151%

    No Known Activations