© 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. 7-RESID-POST-AA
    6. 35969
    Prev
    Next
    INDEX
    Explanations

    code properties/attributes

    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
     Gan
    -0.07
    ssel
    -0.07
    parity
    -0.07
    constitution
    -0.07
    ovel
    -0.06
    cock
    -0.06
    ooled
    -0.06
    BN
    -0.06
     武
    -0.06
    港
    -0.06
    POSITIVE LOGITS
     doldur
    0.06
    adb
    0.06
    larınızı
    0.06
    -स
    0.06
     imaginative
    0.06
    Ce
    0.06
    easy
    0.06
    (parts
    0.06
    ?>
    0.06
     Bölüm
    0.06
    Activations Density 0.022%

    No Known Activations