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. 81198
    Prev
    Next
    INDEX
    Explanations

    online content creation

    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
    -forward
    -0.06
     collecting
    -0.06
    predicate
    -0.06
    !=-
    -0.06
     reflexivity
    -0.06
    �
    -0.06
     Macro
    -0.06
    living
    -0.06
     liv
    -0.06
    -mf
    -0.06
    POSITIVE LOGITS
     cherish
    0.07
     AMAZ
    0.07
    Kom
    0.06
     efter
    0.06
     Plus
    0.06
    aggi
    0.06
     RuntimeError
    0.06
    anın
    0.06
     Lakers
    0.06
    ğın
    0.06
    Activations Density 0.014%

    No Known Activations