© 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. 93484
    Prev
    Next
    INDEX
    Explanations

    territory and divisions

    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
    "Oh
    -0.07
     Kn
    -0.07
    حدث
    -0.07
     brains
    -0.06
    $con
    -0.06
     algumas
    -0.06
    “Oh
    -0.06
     complaining
    -0.06
     plus
    -0.06
     ['
    -0.06
    POSITIVE LOGITS
     territory
    0.12
     Terra
    0.10
     territories
    0.09
     Terr
    0.09
     TNT
    0.08
     terrain
    0.08
    ентами
    0.08
    territ
    0.08
     Territory
    0.08
     Terrain
    0.08
    Activations Density 0.009%

    No Known Activations