© 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. 69140
    Prev
    Next
    INDEX
    Explanations

    ative relevant

    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
    Achie
    -0.07
    _App
    -0.06
    atch
    -0.06
    �
    -0.06
    Diff
    -0.06
    яч
    -0.06
    Вы
    -0.06
    _Ptr
    -0.06
    Being
    -0.06
    Kid
    -0.06
    POSITIVE LOGITS
     scientific
    0.08
     cache
    0.07
     miền
    0.07
     demonstr
    0.07
     influx
    0.07
     advertising
    0.07
    .asp
    0.06
     Natural
    0.06
     authorised
    0.06
     production
    0.06
    Activations Density 0.002%

    No Known Activations