© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 7-RESID-POST-AA
    11. 35027
    Prev
    Next
    INDEX
    Explanations

    role

    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
    _on
    -0.08
    ップ
    -0.07
     hastily
    -0.06
     ench
    -0.06
    626
    -0.06
     ihr
    -0.06
    ystem
    -0.06
    Ethernet
    -0.06
     fourn
    -0.06
     ít
    -0.06
    POSITIVE LOGITS
     revolves
    0.07
     significantly
    0.06
     lesbi
    0.06
     emotionally
    0.06
    ssel
    0.06
    ()?;↵
    0.06
     prefix
    0.06
     Medal
    0.06
    杀
    0.06
     investing
    0.06
    Activations Density 0.001%

    No Known Activations