© 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. 54889
    Prev
    Next
    INDEX
    Explanations

    return

    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
    ['
    -0.06
     materials
    -0.06
    �
    -0.06
    _tri
    -0.06
     امنیت
    -0.06
     Intervention
    -0.06
     then
    -0.06
     ε�
    -0.06
     през
    -0.06
    rade
    -0.06
    POSITIVE LOGITS
    ileceği
    0.07
     boils
    0.06
     ediyor
    0.06
     yemek
    0.06
    Cooldown
    0.06
     dilig
    0.06
    NSUserDefaults
    0.06
    [Byte
    0.06
    .balance
    0.06
     bapt
    0.06
    Activations Density 0.016%

    No Known Activations