© 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. 2984
    Prev
    Next
    INDEX
    Explanations

    genuinely contributing to positive outcomes

    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
    upal
    -0.09
    Äįit
    -0.09
    inho
    -0.09
     Reaper
    -0.09
     slab
    -0.09
    iele
    -0.09
    haul
    -0.09
    905
    -0.08
    olib
    -0.08
    chten
    -0.08
    POSITIVE LOGITS
     impact
    0.20
     Impact
    0.18
    impact
    0.18
     contribution
    0.17
    Impact
    0.16
     make
    0.16
     contribute
    0.16
     making
    0.15
     change
    0.15
     society
    0.15
    Activations Density 0.089%

    No Known Activations