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. 27501
    Prev
    Next
    INDEX
    Explanations

    pronouns

    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
    commend
    -0.07
     Drink
    -0.06
    uesday
    -0.06
     condition
    -0.06
     pneumonia
    -0.06
     sufficient
    -0.06
     thuốc
    -0.06
    owers
    -0.06
    777
    -0.06
     cheg
    -0.06
    POSITIVE LOGITS
    enan
    0.07
    Hex
    0.07
     Spacer
    0.06
     readiness
    0.06
    .matcher
    0.06
     pivot
    0.06
     signer
    0.06
     richt
    0.06
    /re
    0.06
     rgb
    0.06
    Activations Density 0.000%

    No Known Activations