© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 69213
    Prev
    Next
    INDEX
    Explanations

    in

    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
     subur
    -0.07
    _superuser
    -0.07
    	item
    -0.07
    EndTime
    -0.06
    localObject
    -0.06
     onion
    -0.06
    .JOptionPane
    -0.06
    (param
    -0.06
     quá
    -0.06
    inger
    -0.06
    POSITIVE LOGITS
     Original
    0.07
     中
    0.07
     Virgin
    0.07
    Literal
    0.06
    ******
    ↵
    0.06
    _GENER
    0.06
    من
    0.06
     Ms
    0.06
     epoch
    0.06
     exhausted
    0.06
    Activations Density 0.011%

    No Known Activations