© 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. 51817
    Prev
    Next
    INDEX
    Explanations

    source

    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
    َد
    -0.07
    üven
    -0.07
    �
    -0.07
    iae
    -0.06
     halo
    -0.06
    BYTE
    -0.06
     G
    -0.06
    pur
    -0.06
     PED
    -0.06
     these
    -0.06
    POSITIVE LOGITS
    _combined
    0.07
     MOUSE
    0.07
    .isVisible
    0.07
    .dataGridViewTextBoxColumn
    0.07
     españ
    0.07
    *sin
    0.06
     창
    0.06
    (Route
    0.06
    orry
    0.06
    Türk
    0.06
    Activations Density 0.002%

    No Known Activations