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. 110501
    Prev
    Next
    INDEX
    Explanations

    obtain

    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
    いう
    -0.06
    container
    -0.06
    43
    -0.06
    ,System
    -0.06
    、何
    -0.06
    |required
    -0.06
     Charity
    -0.06
    44
    -0.06
    ۱
    -0.06
     spolu
    -0.06
    POSITIVE LOGITS
    エ
    0.07
    ursor
    0.07
     приготов
    0.06
    ardin
    0.06
    rice
    0.06
    axon
    0.06
    _rep
    0.06
     арми
    0.06
     classroom
    0.06
     pred
    0.06
    Activations Density 0.002%

    No Known Activations