© 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. 8508
    Prev
    Next
    INDEX
    Explanations

    ❤️

    np_max-act · gemini-2.0-flash

    short affectionate emojis or heart symbols and other tokens expressing romantic/affectionate sentiment.

    oai_token-act-pair · gpt-5-miniTriggered 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
     confuse
    -0.07
     Garland
    -0.06
     Square
    -0.06
     daughters
    -0.06
    _cut
    -0.06
     conse
    -0.06
    арт
    -0.06
    693
    -0.06
     Ross
    -0.06
     lattice
    -0.06
    POSITIVE LOGITS
    ️
    0.11
    _map
    0.07
    blast
    0.07
     mCurrent
    0.07
    maz
    0.06
    зація
    0.06
    :int
    0.06
     PLUGIN
    0.06
     　 　 　 　 　
    0.06
    MD
    0.06
    Activations Density 0.002%

    No Known Activations