© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 93619
    Prev
    Next
    INDEX
    Explanations

    tabla

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tyard
    -0.07
    urse
    -0.07
    refresh
    -0.06
     siendo
    -0.06
    CELL
    -0.06
    /services
    -0.06
     hinges
    -0.06
    .remaining
    -0.06
     la
    -0.06
    ılmaktadır
    -0.06
    POSITIVE LOGITS
     tabla
    0.24
    Tabla
    0.11
     dopamine
    0.10
    tabla
    0.10
     tabela
    0.07
     stays
    0.06
     Pap
    0.06
    Apache
    0.06
     inaug
    0.06
     порт
    0.06
    Activations Density 0.001%

    No Known Activations