© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 5350
    Prev
    Next
    INDEX
    Explanations

    garbled non-latin characters

    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
    .MixedReality
    -0.07
    ãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢ
    -0.07
    /of
    -0.07
     ëħĦëıĦë³Ħ
    -0.07
    ap
    -0.07
     Perez
    -0.07
    _ptrs
    -0.07
     Legacy
    -0.07
     bufsize
    -0.07
     (!((
    -0.07
    POSITIVE LOGITS
    ¶Į
    0.13
    ******č\n
    0.11
    <|begin_of_text|>
    0.10
    ³Øª
    0.10
    .Formatter
    0.10
    ³ç´°
    0.10
    įng
    0.10
    %č\n
    0.10
    łéĻ¤
    0.09
    EMPLARY
    0.09
    Activations Density 0.789%

    No Known Activations