© 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
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 34453
    Prev
    Next
    INDEX
    Explanations

    States

    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
     mice
    -0.07
     Triangle
    -0.07
    <quote
    -0.06
    .sep
    -0.06
    (gs
    -0.06
    enser
    -0.06
     Led
    -0.06
    CACHE
    -0.06
    130
    -0.06
    Central
    -0.06
    POSITIVE LOGITS
    λιά
    0.06
    ,并
    0.06
    सम
    0.06
    rå
    0.06
    OWL
    0.06
    emales
    0.06
     karak
    0.06
     employers
    0.06
    	op
    0.06
    andex
    0.06
    Activations Density 0.008%

    No Known Activations