© 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. 76231
    Prev
    Next
    INDEX
    Explanations

    .M

    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
     �
    -0.07
     motorcycles
    -0.06
     anthropology
    -0.06
     gard
    -0.06
     multicast
    -0.06
     xlim
    -0.06
     Pers
    -0.06
     Vys
    -0.06
    ……。
    -0.06
     slicing
    -0.06
    POSITIVE LOGITS
    лоп
    0.07
    $return
    0.07
    igators
    0.06
    cased
    0.06
     denounced
    0.06
    operative
    0.06
    951
    0.06
    .promise
    0.06
     Phong
    0.06
    270
    0.05
    Activations Density 0.006%

    No Known Activations