© 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. 19-RESID-POST-AA
    6. 118343
    Prev
    Next
    INDEX
    Explanations

    �

    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
    damage
    -0.06
     Fres
    -0.06
     Faction
    -0.06
    土地
    -0.06
     votre
    -0.06
     movable
    -0.06
     klient
    -0.06
     Telerik
    -0.06
     فريق
    -0.06
     ödül
    -0.06
    POSITIVE LOGITS
    عنی
    0.07
     gcc
    0.07
    γει
    0.07
     compensation
    0.07
    [int
    0.07
     zpět
    0.07
    alfa
    0.07
    assoc
    0.07
    izzy
    0.07
    iens
    0.07
    Activations Density 0.002%

    No Known Activations