© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 52965
    Prev
    Next
    INDEX
    Explanations

    Fiction

    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
    ::::
    -0.07
    expenses
    -0.07
    により
    -0.07
     oak
    -0.06
    )sender
    -0.06
     soutěže
    -0.06
    xEB
    -0.06
    SmartPointer
    -0.06
     osm
    -0.06
     UIS
    -0.06
    POSITIVE LOGITS
     Candy
    0.06
    Shopping
    0.06
    rng
    0.06
    Oh
    0.06
    angered
    0.06
    [loc
    0.05
    ッ
    0.05
     Spr
    0.05
    	JOptionPane
    0.05
     potrze
    0.05
    Activations Density 0.413%

    No Known Activations