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. 3-RESID-POST-AA
    6. 95014
    Prev
    Next
    INDEX
    Explanations

    Locations

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     grou
    -0.06
     demasi
    -0.06
    обрет
    -0.06
    achte
    -0.06
     phon
    -0.06
     inter
    -0.06
    oine
    -0.05
    728
    -0.05
     LIC
    -0.05
     fileType
    -0.05
    POSITIVE LOGITS
     včetně
    0.07
    <void
    0.07
    cket
    0.07
    rejected
    0.07
    URRENCY
    0.07
    <Edge
    0.07
    。<
    0.07
    visual
    0.07
     якому
    0.07
     ViewHolder
    0.06
    Activations Density 0.122%

    No Known Activations