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. 122812
    Prev
    Next
    INDEX
    Explanations

    great

    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
    Opcode
    -0.07
     ك
    -0.07
     vyž
    -0.06
     owned
    -0.06
     inscription
    -0.06
     poker
    -0.06
     khiển
    -0.06
     technical
    -0.06
     Onion
    -0.06
    ám
    -0.06
    POSITIVE LOGITS
     great
    0.21
    great
    0.15
     Great
    0.14
     GREAT
    0.13
    Great
    0.11
     greatness
    0.08
    reat
    0.08
     projectName
    0.07
    reta
    0.07
    scal
    0.07
    Activations Density 0.023%

    No Known Activations