© 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
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 121671
    Prev
    Next
    INDEX
    Explanations

    {

    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
     dei
    -0.08
     worsening
    -0.07
    енную
    -0.06
     Ukraine
    -0.06
     drowning
    -0.06
    braska
    -0.06
     فيه
    -0.06
    distinct
    -0.06
     fluoride
    -0.06
     jub
    -0.06
    POSITIVE LOGITS
    (models
    0.11
     част
    0.11
     طر
    0.08
     southwestern
    0.07
     MessageLookup
    0.07
    クロ
    0.07
     レディース
    0.06
    ";
↵
↵
    0.06
    TouchUpInside
    0.06
    mpz
    0.06
    Activations Density 0.004%

    No Known Activations