© 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 (Instruct)
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 57320
    Prev
    Next
    INDEX
    Explanations

    certainty/confidence

    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
    (Tag
    -0.06
    μερ
    -0.06
     кур
    -0.06
     errs
    -0.06
     <->
    -0.06
     decl
    -0.06
     selv
    -0.06
     Millennials
    -0.06
     알
    -0.06
    INET
    -0.06
    POSITIVE LOGITS
    amazon
    0.06
     Bone
    0.06
     crops
    0.06
     Greek
    0.06
    人口
    0.06
    astype
    0.06
     LIC
    0.06
    .addProperty
    0.06
     lipid
    0.06
     ابن
    0.06
    Activations Density 0.027%

    No Known Activations