Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 93959
    Prev
    Next
    INDEX
    Explanations

    AMD

    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
    892
    -0.07
    _sequence
    -0.07
     вияв
    -0.07
     Journey
    -0.07
     twist
    -0.07
    _rb
    -0.07
    982
    -0.06
    بینی
    -0.06
     Libya
    -0.06
    cee
    -0.06
    POSITIVE LOGITS
     AMD
    0.09
    AMD
    0.08
     amd
    0.07
     comply
    0.07
     _↵↵
    0.07
     abund
    0.07
    Authentication
    0.06
    <HashMap
    0.06
     Average
    0.06
     NSRange
    0.06
    Activations Density 0.001%

    No Known Activations