© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 22767
    Prev
    Next
    INDEX
    Explanations

    desirable

    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
    double
    -0.06
    ('#
    -0.06
    جه
    -0.06
     convex
    -0.06
     Yet
    -0.05
     omitted
    -0.05
     jobs
    -0.05
     clue
    -0.05
    퓨터
    -0.05
    	l
    -0.05
    POSITIVE LOGITS
     paranoia
    0.08
    roles
    0.07
     Địa
    0.07
    شناسی
    0.07
    αρίου
    0.07
     России
    0.07
     escalated
    0.07
    _simulation
    0.07
     Revolution
    0.06
    attendance
    0.06
    Activations Density 0.037%

    No Known Activations