© 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. 4540
    Prev
    Next
    INDEX
    Explanations

    boost spirits and morale

    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
    ï¿£
    -0.09
    atas
    -0.09
    ude
    -0.09
    าà¸ĩ
    -0.09
     imb
    -0.09
    '&&
    -0.09
    er
    -0.09
     destino
    -0.09
    izzle
    -0.09
    esk
    -0.09
    POSITIVE LOGITS
    ers
    0.20
    RAP
    0.13
    ed
    0.13
    (boost
    0.12
     spirits
    0.12
    stakes
    0.12
    erville
    0.12
     morale
    0.11
     sag
    0.11
    _FOREACH
    0.11
    Activations Density 0.023%

    No Known Activations