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. 122654
    Prev
    Next
    INDEX
    Explanations

    encyclopedia entries

    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
     pom
    -0.06
     |
    ↵
    -0.06
    [axis
    -0.06
    :y
    -0.06
    ें,
    -0.06
     vůči
    -0.06
    _between
    -0.06
    หา
    -0.06
     bahsed
    -0.06
     chees
    -0.06
    POSITIVE LOGITS
     ↵↵
    0.16
      ↵↵
    0.07
      ↵
    0.07
    BED
    0.07
     Exterior
    0.07
    lood
    0.07
     Mines
    0.06
    Spacing
    0.06
    シ
    0.06
     продолж
    0.06
    Activations Density 0.017%

    No Known Activations