© 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. 3-RESID-POST-AA
    11. 121855
    Prev
    Next
    INDEX
    Explanations

    LaTeX code

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bank
    -0.07
    concert
    -0.06
     bank
    -0.06
    ]},↵
    -0.06
     `\
    -0.06
    .setCurrent
    -0.06
    ociety
    -0.06
    .setTime
    -0.06
    Angel
    -0.06
    <head
    -0.06
    POSITIVE LOGITS
     Louisiana
    0.07
     плав
    0.07
     silky
    0.07
    .enums
    0.07
     ortadan
    0.07
     UIImage
    0.06
    supported
    0.06
     velk
    0.06
     claws
    0.06
     대통령
    0.06
    Activations Density 0.078%

    No Known Activations