© 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. 32896
    Prev
    Next
    INDEX
    Explanations

    special characters or non-English text

    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
    upp
    -0.08
    ãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢ
    -0.08
     ...\n\n\n\n
    -0.07
     poil
    -0.07
     zel
    -0.07
    ç©´
    -0.07
     Grimm
    -0.07
     Gins
    -0.07
     {{\n
    -0.06
    usu
    -0.06
    POSITIVE LOGITS
    ulumi
    0.08
    ·»
    0.08
    anagan
    0.08
    alles
    0.08
    Ñħови
    0.08
    ³Øª
    0.08
    _flg
    0.07
    vůli
    0.07
    <|begin_of_text|>
    0.07
    ofday
    0.07
    Activations Density 0.016%

    No Known Activations