© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 99808
    Prev
    Next
    INDEX
    Explanations

    :

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     needy
    -0.08
     disability
    -0.07
    wk
    -0.07
     perch
    -0.06
     dropout
    -0.06
     inquiry
    -0.06
     Fry
    -0.06
     decide
    -0.06
    ி�
    -0.06
     interest
    -0.06
    POSITIVE LOGITS
    :↵
    0.08
     :↵
    0.07
     ):↵
    0.07
    ):↵
    0.07
    κας
    0.07
    :↵↵
    0.06
    ็กชาย
    0.06
    ":↵
    0.06
    :S
    0.06
    "):↵
    0.06
    Activations Density 0.143%

    No Known Activations