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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 8839
    Prev
    Next
    INDEX
    Explanations

    negations

    np_max-act · gemini-2.0-flash

    The neuron primarily detects personal pronouns (I, you, he, etc.) and their associated auxiliary or negation forms in expressive statements.

    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
     Prevent
    -0.06
    .wx
    -0.06
    Signup
    -0.06
     https
    -0.06
    _authenticated
    -0.06
     Erotic
    -0.06
    řev
    -0.06
     bk
    -0.06
    .stock
    -0.06
    Sarah
    -0.05
    POSITIVE LOGITS
    ÃO
    0.07
    .Ş
    0.06
    STANCE
    0.06
     PLAY
    0.06
    .Expressions
    0.06
    ОР
    0.06
     city
    0.06
     expression
    0.06
    /o
    0.06
     بزر
    0.06
    Activations Density 0.028%

    No Known Activations