© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 34987
    Prev
    Next
    INDEX
    Explanations

    ral

    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
     screaming
    -0.06
     enums
    -0.06
    .Absolute
    -0.06
     nv
    -0.06
    porter
    -0.06
    .Events
    -0.06
     Regulations
    -0.06
    pagina
    -0.06
     preached
    -0.06
    .Send
    -0.06
    POSITIVE LOGITS
    込み
    0.07
    (fl
    0.07
     حالة
    0.06
    ック
    0.06
    ccion
    0.06
     châu
    0.06
    شة
    0.06
     arası
    0.06
     ülkenin
    0.06
    ớt
    0.06
    Activations Density 0.123%

    No Known Activations