© 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. 56028
    Prev
    Next
    INDEX
    Explanations

    presented the same way

    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
    EMPLARY
    -0.11
     -*-č\n
    -0.10
    thon
    -0.09
    esub
    -0.09
    à¸Ĺย
    -0.09
    ıa
    -0.09
    bé
    -0.08
    ordo
    -0.08
    ëħ
    -0.08
    ADR
    -0.08
    POSITIVE LOGITS
     correct
    0.17
     consistent
    0.16
     exactly
    0.15
     correctly
    0.15
     accurate
    0.13
     Correct
    0.13
    æŃ£ç¡®
    0.13
     ver
    0.12
    Correct
    0.12
     accurately
    0.12
    Activations Density 0.029%

    No Known Activations