Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 94351
    Prev
    Next
    INDEX
    Explanations

    to

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    INSTALL
    -0.07
    енной
    -0.07
     desserts
    -0.06
    ذار
    -0.06
    ми
    -0.06
     š
    -0.06
    هر
    -0.06
     featured
    -0.06
    (ch
    -0.06
     SCORE
    -0.06
    POSITIVE LOGITS
    илась
    0.07
     funciona
    0.07
    キング
    0.07
     이벤트
    0.06
    ーブ
    0.06
    şiv
    0.06
     omission
    0.06
     practition
    0.06
    책
    0.06
     overflowing
    0.06
    Activations Density 0.003%

    No Known Activations