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. 61302
    Prev
    Next
    INDEX
    Explanations

    the

    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
    库
    -0.06
     aprender
    -0.06
    err
    -0.06
    Eff
    -0.06
    IMPORTANT
    -0.06
    Accessory
    -0.06
    collectionView
    -0.05
    _EX
    -0.05
    ickest
    -0.05
    /container
    -0.05
    POSITIVE LOGITS
    اکی
    0.07
    inness
    0.07
    cpy
    0.07
    classified
    0.07
    тен
    0.06
     vaping
    0.06
     Prize
    0.06
     registered
    0.06
    	timer
    0.06
    로나
    0.06
    Activations Density 0.000%

    No Known Activations