© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 46258
    Prev
    Next
    INDEX
    Explanations

    UEFA/European soccer

    np_max-act · gemini-2.0-flash

    biographical information about football players and managers.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    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
     Gü
    -0.07
    perate
    -0.07
    etiyle
    -0.07
     OSS
    -0.06
    _win
    -0.06
    erves
    -0.06
    wake
    -0.06
    ват
    -0.06
    ville
    -0.06
    (INPUT
    -0.06
    POSITIVE LOGITS
    Effect
    0.06
    */),
    0.06
    ："+
    0.06
    %',↵
    0.06
    -blind
    0.06
     riches
    0.06
     sher
    0.06
    咲
    0.06
    灵
    0.06
     treating
    0.06
    Activations Density 0.003%

    No Known Activations