© 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. 76286
    Prev
    Next
    INDEX
    Explanations

    history, origins of agriculture

    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
     preempt
    -0.07
    XB
    -0.07
    客户
    -0.06
    fgang
    -0.06
    rup
    -0.06
    Contacts
    -0.06
     GBP
    -0.06
    _io
    -0.06
    .Option
    -0.06
     OPTION
    -0.06
    POSITIVE LOGITS
     Yatırım
    0.06
    عا
    0.06
    optera
    0.06
     команд
    0.06
     Emily
    0.06
    -prom
    0.06
    nder
    0.06
    σταν
    0.06
     racer
    0.06
    μαι
    0.06
    Activations Density 0.023%

    No Known Activations