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. 15-RESID-POST-AA
    6. 121936
    Prev
    Next
    INDEX
    Explanations

    Need/Request

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     horses
    -0.07
     scant
    -0.07
     Fathers
    -0.06
     MOUSE
    -0.06
     Carp
    -0.06
     judged
    -0.06
     Libert
    -0.06
    orses
    -0.06
    Objects
    -0.06
     Manifest
    -0.06
    POSITIVE LOGITS
    최고
    0.08
     Nielsen
    0.07
    那些
    0.07
    /signup
    0.06
    虫
    0.06
    帮
    0.06
     JADX
    0.06
    ís
    0.06
     By
    0.06
    Donate
    0.06
    Activations Density 0.032%

    No Known Activations