© 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 (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 52927
    Prev
    Next
    INDEX
    Explanations

    -to

    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
     insurers
    -0.07
     diff
    -0.07
    Speak
    -0.06
    ugh
    -0.06
    -book
    -0.06
     ld
    -0.06
     cloak
    -0.06
     Loads
    -0.06
     aired
    -0.06
    _back
    -0.06
    POSITIVE LOGITS
     Ama
    0.07
    consts
    0.06
     proti
    0.06
    aticon
    0.06
    听到
    0.06
     الجديد
    0.06
    ها
    0.06
     플레이
    0.06
    ื
    0.06
     जल
    0.06
    Activations Density 0.008%

    No Known Activations