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. 5384
    Prev
    Next
    INDEX
    Explanations

    descriptive texts

    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
     dumping
    -0.07
    _receiver
    -0.07
    analyze
    -0.07
     preparations
    -0.07
     использу
    -0.07
    _delivery
    -0.06
    pd
    -0.06
     rash
    -0.06
    �y
    -0.06
     BJP
    -0.06
    POSITIVE LOGITS
    ──
    0.06
    schools
    0.06
    .activate
    0.06
    DIRECTORY
    0.06
    ondon
    0.06
    CTSTR
    0.06
    )$_
    0.06
    네요
    0.06
    カード
    0.06
     airs
    0.06
    Activations Density 0.194%

    No Known Activations