© 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. 4846
    Prev
    Next
    INDEX
    Explanations

    reach or approach movement

    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
     dusk
    -0.09
    datum
    -0.09
    ieve
    -0.09
    istrovstvÃŃ
    -0.09
    erosis
    -0.09
    umbling
    -0.09
     repet
    -0.09
    ingt
    -0.09
    inx
    -0.08
     crawler
    -0.08
    POSITIVE LOGITS
     approach
    0.27
     reached
    0.26
     approached
    0.25
     reach
    0.25
     Approach
    0.25
     approaches
    0.25
    appro
    0.24
    Appro
    0.23
     Appro
    0.23
     reaches
    0.23
    Activations Density 0.031%

    No Known Activations