© 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. 62588
    Prev
    Next
    INDEX
    Explanations

    travel between locations, prove that, before calling

    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
    ModelProperty
    -0.09
    ¶Į
    -0.09
    ¦æĥħ
    -0.09
    _INCREMENT
    -0.08
    odial
    -0.08
    /../
    -0.08
    įng
    -0.08
    ÂĢÂĢ
    -0.08
    ventas
    -0.08
    âĹĭ
    -0.08
    POSITIVE LOGITS
    .scalablytyped
    0.12
     ########################################################################
    0.08
    âĻª\n\n
    0.08
    ','=',$
    0.07
    ...\n\n\n\n
    0.07
    ’;s
    0.07
    izontally
    0.07
    527
    0.07
     Marino
    0.07
    kara
    0.07
    Activations Density 0.143%

    No Known Activations