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. 94802
    Prev
    Next
    INDEX
    Explanations

    America/Europe

    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
     War
    -0.07
     rp
    -0.06
    	swap
    -0.06
    год
    -0.06
    した
    -0.06
     proportion
    -0.06
    (rate
    -0.06
     sulfur
    -0.06
     getInt
    -0.06
     Southeast
    -0.06
    POSITIVE LOGITS
    edTextBox
    0.07
     yüksel
    0.06
    ;")↵
    0.06
    .store
    0.06
    ;}↵
    0.06
     onClose
    0.06
    '];?>"
    0.06
    ().'
    0.06
    (Bytes
    0.06
    orsk
    0.06
    Activations Density 0.023%

    No Known Activations