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. 80859
    Prev
    Next
    INDEX
    Explanations

    Academic publications

    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
     bondage
    -0.06
     kost
    -0.06
    _blue
    -0.06
    .itemId
    -0.06
     здесь
    -0.06
     arising
    -0.06
     '=
    -0.06
    Asian
    -0.06
     sprint
    -0.06
     Ashley
    -0.05
    POSITIVE LOGITS
    �
    0.07
     jon
    0.07
    '>".$
    0.06
    Έ
    0.06
    .gridColumn
    0.06
     Metal
    0.06
    桃
    0.06
    €�
    0.06
     Oz
    0.06
     �
    0.06
    Activations Density 0.006%

    No Known Activations