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. 81320
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    phrases related to personal experiences and emotions.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    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
     dietary
    -0.07
    ({↵
    -0.07
    اری
    -0.06
    ->_
    -0.06
     Bytes
    -0.06
    _multiplier
    -0.06
     views
    -0.06
     Stunden
    -0.06
     eggs
    -0.06
    满
    -0.06
    POSITIVE LOGITS
    ICI
    0.07
    종
    0.06
    icester
    0.06
     국가
    0.06
     دل
    0.06
    sson
    0.06
    ancement
    0.06
    jc
    0.06
     العربي
    0.06
    ato
    0.06
    Activations Density 0.002%

    No Known Activations