© 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. 18407
    Prev
    Next
    INDEX
    Explanations

    positive communication and information

    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
    <|begin_of_text|>
    -0.08
    ******č\n
    -0.08
     âĸij
    -0.07
    \tTokenName
    -0.07
     âĵĺ
    -0.07
    \brief
    -0.07
     diseñador
    -0.07
    ï¸
    -0.07
    achuset
    -0.07
    HasBeenSet
    -0.07
    POSITIVE LOGITS
     cigaret
    0.07
     Certain
    0.07
     certain
    0.07
    umbs
    0.07
    ,,
    0.06
    quette
    0.06
    646
    0.06
    -related
    0.06
    ==(
    0.06
     Isles
    0.06
    Activations Density 0.003%

    No Known Activations