Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 92225
    Prev
    Next
    INDEX
    Explanations

    code and math

    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
    _tim
    -0.07
     tình
    -0.07
    یه
    -0.07
     meeting
    -0.07
     ={
    -0.06
    elapsed
    -0.06
    cesso
    -0.06
    uator
    -0.06
     colleg
    -0.06
     anlaş
    -0.06
    POSITIVE LOGITS
     justifyContent
    0.07
     Why
    0.07
     complicated
    0.06
     Ferguson
    0.06
    _tool
    0.06
    _configs
    0.06
     때문
    0.06
     конс
    0.06
    }]
    0.06
    _NODE
    0.06
    Activations Density 0.003%

    No Known Activations