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. 95124
    Prev
    Next
    INDEX
    Explanations

    programming code

    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
     ammunition
    -0.06
    Except
    -0.06
    Nh
    -0.06
    ascus
    -0.06
    isicing
    -0.06
    ومی
    -0.06
    JR
    -0.06
     Bare
    -0.06
     titular
    -0.06
    istrator
    -0.05
    POSITIVE LOGITS
    ")+
    0.07
    egt
    0.07
    Mutex
    0.06
    avr
    0.06
     unauthorized
    0.06
    adir
    0.06
    elle
    0.06
    ikki
    0.06
     lối
    0.06
    (Auth
    0.06
    Activations Density 0.028%

    No Known Activations