© 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. 2275
    Prev
    Next
    INDEX
    Explanations

    `label` and `maintaining`

    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
    ¶Į
    -0.11
    ******č\n
    -0.10
     addCriterion
    -0.09
    ĮĴ
    -0.09
     PÅĺ
    -0.09
    <|begin_of_text|>
    -0.09
    (íģ¬ê¸°
    -0.09
    ÂĢÂĢ
    -0.09
    ³ç´°
    -0.09
    .habbo
    -0.09
    POSITIVE LOGITS
    --
    0.09
    /be
    0.08
    redd
    0.07
     file
    0.07
     map
    0.07
     album
    0.07
     nav
    0.07
    :\"
    0.07
     Brook
    0.07
    odes
    0.07
    Activations Density 0.078%

    No Known Activations