© 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. 51730
    Prev
    Next
    INDEX
    Explanations

    articles and "to be" verbs

    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
    Mah
    -0.06
    Yet
    -0.06
     Permission
    -0.06
    унк
    -0.06
    кол
    -0.06
    documento
    -0.06
    ційно
    -0.06
    Pour
    -0.06
    —from
    -0.06
    isk
    -0.06
    POSITIVE LOGITS
    (library
    0.08
    >Description
    0.07
    UpperCase
    0.07
     analyses
    0.07
    ♪↵↵
    0.07
     autopsy
    0.06
    -Encoding
    0.06
    اهر
    0.06
     cocci
    0.06
    jk
    0.06
    Activations Density 0.022%

    No Known Activations