© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 76481
    Prev
    Next
    INDEX
    Explanations

    Code and technical language

    np_max-act · gemini-2.0-flash

    code- and markup-like syntax elements (e.g., brackets, braces, quotes, backticks, and underscore-delimited identifiers) that signal structured snippets or configuration.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    енный
    -0.06
    -0.06
    (KP
    -0.06
    _transaksi
    -0.06
    %);↵
    -0.06
    _FINE
    -0.06
     MAX
    -0.06
    .files
    -0.06
     ########################
    -0.06
    Número
    -0.06
    POSITIVE LOGITS
     Consulting
    0.06
     �
    0.06
     ^^
    0.06
    /Sh
    0.05
    usb
    0.05
     參
    0.05
    력이
    0.05
    emple
    0.05
    stretch
    0.05
    地说
    0.05
    Activations Density 6.757%

    No Known Activations