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. 80842
    Prev
    Next
    INDEX
    Explanations

    ly

    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
    prestashop
    -0.06
     전
    -0.06
     consultancy
    -0.06
    测
    -0.06
     beste
    -0.06
     إذا
    -0.06
    PROTO
    -0.06
    棚
    -0.06
    .prepend
    -0.06
     zoek
    -0.05
    POSITIVE LOGITS
    .BooleanField
    0.07
     }]
    0.07
     ISSN
    0.07
    宽
    0.06
    'H
    0.06
     firing
    0.06
    =https
    0.06
    -story
    0.06
     frameborder
    0.06
     Listings
    0.06
    Activations Density 0.080%

    No Known Activations