© 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. 4397
    Prev
    Next
    INDEX
    Explanations

    state or condition

    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
     Howell
    -0.12
    amac
    -0.11
    vang
    -0.10
     Sachs
    -0.09
    vron
    -0.09
    imensional
    -0.08
     Henderson
    -0.08
     highest
    -0.08
    åij½
    -0.08
     nam
    -0.08
    POSITIVE LOGITS
     changed
    0.19
     Changed
    0.15
    changed
    0.14
    Changed
    0.13
     ë³Ģê²½
    0.13
     preserved
    0.12
    å¤īæĽ´
    0.12
     kept
    0.11
     change
    0.11
    -change
    0.11
    Activations Density 0.130%

    No Known Activations