© 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
    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. 79411
    Prev
    Next
    INDEX
    Explanations

    be

    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
    ,strlen
    -0.08
     Wat
    -0.07
     tablespoons
    -0.06
    Türk
    -0.06
    .assertj
    -0.06
    ]);
    -0.06
    干
    -0.06
     tents
    -0.06
    елення
    -0.06
    .panelControl
    -0.06
    POSITIVE LOGITS
     SECOND
    0.07
    consulta
    0.07
    ’nun
    0.06
    ạ
    0.06
     controversial
    0.06
     prem
    0.06
    „ظ
    0.06
    -special
    0.06
    ounder
    0.06
    =====↵
    0.06
    Activations Density 0.104%

    No Known Activations