© 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. 3-RESID-POST-AA
    6. 94008
    Prev
    Next
    INDEX
    Explanations

    communication and information

    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
    效果
    -0.07
    Spr
    -0.07
    rolls
    -0.07
     именно
    -0.06
    бор
    -0.06
    Fs
    -0.06
    顿
    -0.06
    imgs
    -0.06
    Fully
    -0.06
    achte
    -0.06
    POSITIVE LOGITS
    IllegalAccessException
    0.06
    apixel
    0.06
     setTitleColor
    0.06
    	GL
    0.06
    WEST
    0.06
     Messiah
    0.06
     бізнес
    0.06
    \":{\"
    0.06
    (pic
    0.06
    idency
    0.06
    Activations Density 0.133%

    No Known Activations