Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 81304
    Prev
    Next
    INDEX
    Explanations

    biological studies

    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
    emer
    -0.07
     BIG
    -0.06
     plastics
    -0.06
     breathe
    -0.06
     imitation
    -0.06
     ble
    -0.06
    /template
    -0.06
    Describe
    -0.06
     Loren
    -0.06
     deniz
    -0.06
    POSITIVE LOGITS
    だけど
    0.07
     functionName
    0.06
    *",
    0.06
    ouses
    0.06
    _PAD
    0.06
    ْد
    0.06
    目を
    0.06
    ,她
    0.06
    ,-
    0.06
     Prostitutas
    0.06
    Activations Density 0.030%

    No Known Activations