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. 86013
    Prev
    Next
    INDEX
    Explanations

    Expressing opinions/viewpoints

    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
      
    -0.07
    Id
    -0.07
       
    -0.06
     revelation
    -0.06
    _{
    -0.06
     hailed
    -0.06
     Triangle
    -0.06
    мами
    -0.06
     EC
    -0.06
     Mystery
    -0.06
    POSITIVE LOGITS
    qm
    0.07
    微软雅黑
    0.06
     trò
    0.06
    .sessions
    0.06
    -delay
    0.06
    .DATA
    0.06
    _INITIALIZER
    0.06
    .addData
    0.06
    (UnmanagedType
    0.06
    	when
    0.06
    Activations Density 0.061%

    No Known Activations