Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 77423
    Prev
    Next
    INDEX
    Explanations

    Adjectives ending in -ive/-ative/-ptive

    np_max-act · gemini-2.0-flash
    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
    _ul
    -0.07
     Lund
    -0.07
    (al
    -0.07
     until
    -0.07
     Year
    -0.07
     cán
    -0.07
    el
    -0.07
    ll
    -0.07
     sun
    -0.07
     all
    -0.07
    POSITIVE LOGITS
    ive
    0.11
    itive
    0.10
    rente
    0.09
     Protective
    0.09
    ative
    0.09
    aptive
    0.09
    دي
    0.09
    IVE
    0.08
     Matte
    0.08
    ائي
    0.08
    Activations Density 0.112%

    No Known Activations