© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 17989
    Prev
    Next
    INDEX
    Explanations

    scientist names

    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
     biochemical
    -0.07
    chy
    -0.07
     medium
    -0.07
     completes
    -0.06
     fruit
    -0.06
     faculties
    -0.06
    .sel
    -0.06
     підприємств
    -0.06
     Apartment
    -0.06
     Wholesale
    -0.06
    POSITIVE LOGITS
    	restore
    0.07
     dung
    0.07
    .START
    0.06
    -Semit
    0.06
    Done
    0.06
     شو
    0.06
    -track
    0.06
    pee
    0.06
    .trans
    0.06
    mf
    0.06
    Activations Density 0.008%

    No Known Activations