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. 101054
    Prev
    Next
    INDEX
    Explanations

    heart

    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
     Uzbek
    -0.06
     palp
    -0.06
     Det
    -0.06
    ango
    -0.06
     gaze
    -0.06
     پذیر
    -0.06
    bre
    -0.06
    Services
    -0.06
    dda
    -0.06
    li
    -0.06
    POSITIVE LOGITS
     만들
    0.08
    how
    0.07
     how
    0.07
    Hz
    0.07
    (entry
    0.07
     hearts
    0.07
     revolving
    0.07
     heart
    0.07
     shows
    0.07
     receiver
    0.07
    Activations Density 0.008%

    No Known Activations