© 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. 36015
    Prev
    Next
    INDEX
    Explanations

    çĿĢ followed by éijij, æİ¥ followed by åı£

    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
    431
    -0.10
    ights
    -0.09
    lick
    -0.09
    vik
    -0.09
     Dak
    -0.09
    quist
    -0.09
    '
    -0.09
    ards
    -0.09
    (
    -0.08
    atts
    -0.08
    POSITIVE LOGITS
     revel
    0.11
     Rah
    0.10
    terra
    0.10
     addCriterion
    0.10
     Raq
    0.09
    iyah
    0.09
     iParam
    0.09
     sourceMappingURL
    0.09
    /epl
    0.09
    à¹Ħà¸Ĺย
    0.09
    Activations Density 0.068%

    No Known Activations