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. 86285
    Prev
    Next
    INDEX
    Explanations

    okia

    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
    /parser
    -0.07
    _Long
    -0.07
    ="--
    -0.07
     الك
    -0.06
    ailability
    -0.06
    chimp
    -0.06
     bio
    -0.06
    izados
    -0.06
    _SETUP
    -0.06
    Port
    -0.06
    POSITIVE LOGITS
     Nokia
    0.14
    okia
    0.10
     Pessoa
    0.07
     recep
    0.07
     QWidget
    0.07
     Papua
    0.06
     percept
    0.06
     Bian
    0.06
     Slovakia
    0.06
    OAuth
    0.06
    Activations Density 0.001%

    No Known Activations