© 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. 15-RESID-POST-AA
    6. 115213
    Prev
    Next
    INDEX
    Explanations

    forgetting and pretending

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _BC
    -0.07
    勝
    -0.06
    �
    -0.06
    _cached
    -0.06
     Ves
    -0.06
    erialization
    -0.06
    BILL
    -0.06
     dinh
    -0.06
    uf
    -0.06
    Sony
    -0.06
    POSITIVE LOGITS
    ❤
    0.06
    jury
    0.06
     mắc
    0.06
    .getInt
    0.06
    :↵↵↵↵
    0.06
     ✔
    0.06
    iten
    0.06
     мяг
    0.06
    ]
    0.06
    owane
    0.06
    Activations Density 0.028%

    No Known Activations