© 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. 77137
    Prev
    Next
    INDEX
    Explanations

    "to be" verb forms

    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
    та
    -0.07
    bero
    -0.07
    orf
    -0.07
    nicas
    -0.07
    ons
    -0.06
    ukes
    -0.06
    $o
    -0.06
    ressing
    -0.06
     Flint
    -0.06
    -def
    -0.06
    POSITIVE LOGITS
     sahip
    0.07
     배우
    0.06
    DIRECT
    0.06
     upward
    0.06
    .itemView
    0.06
    portlet
    0.06
     S
    0.06
    名字
    0.06
     formula
    0.06
    .MouseEvent
    0.06
    Activations Density 0.230%

    No Known Activations