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. 27-RESID-POST-AA
    6. 109264
    Prev
    Next
    INDEX
    Explanations

    was

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     transmitted
    -0.07
     Brief
    -0.07
    Quit
    -0.07
    ío
    -0.07
    ‌اند
    -0.06
    输出
    -0.06
    -tm
    -0.06
     amounts
    -0.06
     serv
    -0.06
    (active
    -0.06
    POSITIVE LOGITS
     happens
    0.06
     بج
    0.06
     saúde
    0.06
     Pharm
    0.06
    "She
    0.06
     Det
    0.06
    _AUT
    0.06
     airspace
    0.06
     �
    0.05
    uluğ
    0.05
    Activations Density 0.084%

    No Known Activations