© 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. 19-RESID-POST-AA
    11. 87569
    Prev
    Next
    INDEX
    Explanations

    privilege

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CLEAR
    -0.07
     Statements
    -0.07
     blot
    -0.07
     gaping
    -0.06
     CET
    -0.06
     antagon
    -0.06
     DAG
    -0.06
     کاهش
    -0.06
    .Look
    -0.06
     zorun
    -0.06
    POSITIVE LOGITS
     privilege
    0.10
     privileged
    0.08
     privile
    0.08
     podnik
    0.08
    (ev
    0.08
     Priv
    0.07
     privileges
    0.07
     業
    0.07
    divide
    0.07
     прив
    0.07
    Activations Density 0.004%

    No Known Activations