© 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. 15-RESID-POST-AA
    11. 1490
    Prev
    Next
    INDEX
    Explanations

    race

    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
     goog
    -0.08
     Daemon
    -0.07
    908
    -0.07
     plaint
    -0.07
    submitButton
    -0.07
     Willow
    -0.07
     ngOn
    -0.06
    Plant
    -0.06
     consolidation
    -0.06
    407
    -0.06
    POSITIVE LOGITS
     race
    0.13
     Race
    0.12
     races
    0.11
    Race
    0.10
     rac
    0.08
    ké
    0.08
    ice
    0.08
     Races
    0.08
     IsActive
    0.07
    cle
    0.07
    Activations Density 0.016%

    No Known Activations