© 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. 94094
    Prev
    Next
    INDEX
    Explanations

    Code and UI elements

    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
    λαν
    -0.08
    coal
    -0.07
     sok
    -0.06
    pecia
    -0.06
     getById
    -0.06
    *pow
    -0.06
    Formula
    -0.06
     Skipping
    -0.06
    standard
    -0.06
     webs
    -0.06
    POSITIVE LOGITS
     bên
    0.06
     grievances
    0.06
     humiliating
    0.06
     whale
    0.06
     دادن
    0.06
     attendant
    0.06
    (chain
    0.06
     generado
    0.06
     Disease
    0.06
     pronounced
    0.06
    Activations Density 0.067%

    No Known Activations