© 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. 7-RESID-POST-AA
    11. 32207
    Prev
    Next
    INDEX
    Explanations

    i

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Preparation
    -0.06
    Term
    -0.06
    -debug
    -0.06
    JO
    -0.06
    restaurant
    -0.06
    STRUCT
    -0.06
    254
    -0.06
    NX
    -0.06
     sortie
    -0.06
     drives
    -0.06
    POSITIVE LOGITS
    호
    0.06
     unsubscribe
    0.06
    筒
    0.06
    ğimiz
    0.06
    kelig
    0.06
     vehicle
    0.06
    AMAGE
    0.06
    \\/
    0.06
    ?family
    0.06
     Tub
    0.06
    Activations Density 0.279%

    No Known Activations