© 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. 25367
    Prev
    Next
    INDEX
    Explanations

    rpg, rica, raro, riqueza

    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
    isk
    -0.13
    outer
    -0.12
    ange
    -0.12
    unn
    -0.12
    ipple
    -0.11
    ated
    -0.11
    оÑģ
    -0.11
    acers
    -0.11
    aise
    -0.10
    ATE
    -0.10
    POSITIVE LOGITS
    iq
    0.13
     espect
    0.12
    yalty
    0.12
     ec
    0.11
    aras
    0.11
     educ
    0.11
    onga
    0.10
    gression
    0.10
    iqu
    0.10
    ikal
    0.10
    Activations Density 0.037%

    No Known Activations