© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 93868
    Prev
    Next
    INDEX
    Explanations

    any

    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
    (flow
    -0.07
    createForm
    -0.06
    (movie
    -0.06
    []
↵
    -0.06
    ,"%
    -0.06
    ieties
    -0.06
     Boston
    -0.06
    зь
    -0.06
    شور
    -0.06
     share
    -0.06
    POSITIVE LOGITS
    emey
    0.06
     unify
    0.06
    任
    0.06
    307
    0.06
    /articles
    0.06
    _fs
    0.06
     aute
    0.06
    iều
    0.06
    迫
    0.06
     Damian
    0.06
    Activations Density 0.015%

    No Known Activations