© 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. 71700
    Prev
    Next
    INDEX
    Explanations

    Testable/falsifiable theories

    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
    .Convert
    -0.06
    	now
    -0.06
     curs
    -0.06
     pela
    -0.06
    entar
    -0.06
    hunt
    -0.06
     göster
    -0.06
    Requires
    -0.06
     produto
    -0.05
    oucí
    -0.05
    POSITIVE LOGITS
     порядок
    0.07
     Malaysian
    0.06
     nurse
    0.06
     商品
    0.06
     MouseEventArgs
    0.06
            ↵        ↵        ↵
    0.06
    +N
    0.06
    ufreq
    0.06
    _MAC
    0.06
        ↵    ↵    ↵    ↵
    0.06
    Activations Density 0.037%

    No Known Activations