© 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. 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. 58735
    Prev
    Next
    INDEX
    Explanations

    explicit

    np_max-act · gemini-2.0-flash

    The neuron fires on adverbial qualifiers (e.g. “explicitly,” “actually,” “clearly”) that add emphasis or clarification.

    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
     searchString
    -0.08
    .richTextBox
    -0.07
    gettext
    -0.07
     exported
    -0.07
    _LAT
    -0.07
     slaughter
    -0.07
     DatePicker
    -0.06
     arrogance
    -0.06
    Designed
    -0.06
     انرژی
    -0.06
    POSITIVE LOGITS
     sahibi
    0.07
     specialised
    0.07
    ство
    0.07
    VEN
    0.06
    ANGE
    0.06
    isinde
    0.06
    inia
    0.06
     noe
    0.06
     Âu
    0.06
    ма
    0.06
    Activations Density 0.024%

    No Known Activations