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. 15-RESID-POST-AA
    6. 31221
    Prev
    Next
    INDEX
    Explanations

    for

    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
     setback
    -0.08
     decipher
    -0.06
    uble
    -0.06
    _RECV
    -0.06
    (call
    -0.06
    ลด
    -0.06
    뮤
    -0.06
     GOT
    -0.06
    -stage
    -0.06
     مسیر
    -0.06
    POSITIVE LOGITS
    ал
    0.07
    496
    0.07
    ги
    0.07
     Buddhism
    0.07
    대의
    0.07
     Europeans
    0.07
    441
    0.06
    (components
    0.06
    ิมพ
    0.06
     Femme
    0.06
    Activations Density 0.002%

    No Known Activations