© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 28314
    Prev
    Next
    INDEX
    Explanations

    Personal opinions/anecdotes

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ตร
    -0.07
     multi
    -0.07
     schöne
    -0.07
     newly
    -0.06
    足球
    -0.06
    .Automation
    -0.06
    氧
    -0.06
     Scaffold
    -0.06
     тел
    -0.06
     سان
    -0.06
    POSITIVE LOGITS
    ued
    0.07
     hypertension
    0.06
    """
    ↵
    ↵
    0.06
    _Tool
    0.06
     '}';↵
    0.06
    stress
    0.06
     taxpayer
    0.06
     Talent
    0.06
     Isles
    0.06
     Lady
    0.06
    Activations Density 0.001%

    No Known Activations