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. 11-RESID-POST-AA
    6. 75742
    Prev
    Next
    INDEX
    Explanations

    ammonia

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     intertwined
    -0.07
    etas
    -0.06
    esture
    -0.06
     Lig
    -0.06
    /widget
    -0.06
    lide
    -0.06
     lig
    -0.06
    �i
    -0.06
    �
    -0.06
    avig
    -0.06
    POSITIVE LOGITS
     ammonia
    0.10
     ammon
    0.09
     monastery
    0.07
     Champagne
    0.07
    mia
    0.06
    ../../
    0.06
     vzpom
    0.06
     immedi
    0.06
    Shadow
    0.06
     Marshall
    0.06
    Activations Density 0.003%

    No Known Activations