© 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. 93443
    Prev
    Next
    INDEX
    Explanations

    和

    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
     biology
    -0.06
     bordered
    -0.06
    filer
    -0.06
    ΑΣ
    -0.06
    }{$
    -0.06
     foc
    -0.06
    (Self
    -0.06
     published
    -0.06
     refused
    -0.06
     nhỏ
    -0.06
    POSITIVE LOGITS
    ,rp
    0.08
     Pulse
    0.08
    cccc
    0.07
     Likes
    0.07
    hostname
    0.07
    ListItem
    0.07
    州市
    0.07
     Kris
    0.07
     popularity
    0.06
     Kubernetes
    0.06
    Activations Density 0.002%

    No Known Activations