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. 103956
    Prev
    Next
    INDEX
    Explanations

    code

    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
    GX
    -0.06
     OU
    -0.06
     потому
    -0.06
    ows
    -0.06
    boBox
    -0.06
    lek
    -0.06
    altar
    -0.06
    }>
    ↵
    -0.06
     pole
    -0.06
    .instance
    -0.06
    POSITIVE LOGITS
     Gentle
    0.07
    .arch
    0.06
    har
    0.06
     σύν
    0.06
    -param
    0.06
     eater
    0.06
     Custom
    0.06
     Giải
    0.06
     Idea
    0.06
     Imp
    0.06
    Activations Density 0.013%

    No Known Activations