© 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. 11-RESID-POST-AA
    11. 54292
    Prev
    Next
    INDEX
    Explanations

    restrooms

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on the word “restroom,” detecting mentions of someone going to or being in a restroom.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OTE
    -0.07
    .Expect
    -0.07
    _DDR
    -0.06
     palp
    -0.06
    .generate
    -0.06
    .owl
    -0.06
    쳤다
    -0.06
    quine
    -0.06
     iddia
    -0.06
    ским
    -0.06
    POSITIVE LOGITS
    ﾆ
    0.08
     vfs
    0.06
     क
    0.06
     attach
    0.06
     Liberties
    0.06
    _CI
    0.06
    \Input
    0.06
    -i
    0.06
     humane
    0.06
     stret
    0.06
    Activations Density 0.011%

    No Known Activations