© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 2335
    Prev
    Next
    INDEX
    Explanations

    reciprocate or return 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
    iguous
    -0.09
    amoto
    -0.08
    aeper
    -0.08
    endl
    -0.08
     Chatt
    -0.08
    plr
    -0.08
    oui
    -0.08
     Hlav
    -0.08
    rael
    -0.08
    YNC
    -0.08
    POSITIVE LOGITS
     recip
    0.59
     reciprocal
    0.37
     recipro
    0.35
     return
    0.31
     retour
    0.27
     returned
    0.26
     counter
    0.25
    è¿Ķ
    0.25
    return
    0.25
     retali
    0.24
    Activations Density 0.147%

    No Known Activations