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. 23-RESID-POST-AA
    6. 103909
    Prev
    Next
    INDEX
    Explanations

    mandate

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Je
    -0.07
     Hyde
    -0.07
     Chen
    -0.07
     thirteen
    -0.07
     photographer
    -0.07
     affection
    -0.06
     pressure
    -0.06
    press
    -0.06
     Jeff
    -0.06
    ('~
    -0.06
    POSITIVE LOGITS
    農
    0.08
    ander
    0.08
    AML
    0.08
    ανδ
    0.08
     mand
    0.08
    ند
    0.08
    andr
    0.07
    GN
    0.07
     Mand
    0.07
    andalone
    0.07
    Activations Density 0.062%

    No Known Activations