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. 7326
    Prev
    Next
    INDEX
    Explanations

    F

    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
    '.
    -0.07
    iT
    -0.07
     t
    -0.06
    år
    -0.06
    plně
    -0.06
     ubytování
    -0.06
     Generally
    -0.06
    Directory
    -0.06
     eser
    -0.06
    ıp
    -0.06
    POSITIVE LOGITS
    .flags
    0.07
    donnees
    0.07
     真
    0.07
     конкур
    0.06
     camb
    0.06
     اسپ
    0.06
     강남
    0.06
     beforeSend
    0.06
     vznik
    0.06
     Vuex
    0.06
    Activations Density 0.005%

    No Known Activations