© 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. 20778
    Prev
    Next
    INDEX
    Explanations

    returns, profit, rewards

    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
    undry
    -0.09
    otti
    -0.09
    owell
    -0.09
     Gibbs
    -0.09
    prs
    -0.09
    andel
    -0.09
    udd
    -0.09
    asan
    -0.08
    EDA
    -0.08
    è²»
    -0.08
    POSITIVE LOGITS
     returns
    0.41
     Returns
    0.33
    returns
    0.31
     return
    0.31
    Returns
    0.27
     Return
    0.27
     RETURNS
    0.26
    return
    0.25
    Return
    0.24
    _return
    0.20
    Activations Density 0.061%

    No Known Activations