© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 7706
    Prev
    Next
    INDEX
    Explanations

    short

    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
    ۴
    -0.07
     ambassador
    -0.06
    lista
    -0.06
     incremental
    -0.06
     Symbol
    -0.06
    mě
    -0.06
    usb
    -0.06
    health
    -0.06
     metabolism
    -0.06
    thora
    -0.06
    POSITIVE LOGITS
    donnees
    0.07
    _lat
    0.06
    ‪
    0.06
     Silicone
    0.06
    getTitle
    0.06
    _MORE
    0.06
     연구
    0.06
     DataTypes
    0.06
    =UTF
    0.06
    "])){↵
    0.06
    Activations Density 0.024%

    No Known Activations