© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 92047
    Prev
    Next
    INDEX
    Explanations

    color

    np_max-act · gemini-2.0-flash

    The neuron detects descriptive mentions of colors, patterns, and design attributes in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     plays
    -0.07
     대표
    -0.07
    飯
    -0.07
     Brussels
    -0.07
     pastry
    -0.07
    service
    -0.06
     internacional
    -0.06
     prac
    -0.06
    _platform
    -0.06
     Swedish
    -0.06
    POSITIVE LOGITS
    {EIF
    0.07
    .clear
    0.07
     知
    0.07
    CUDA
    0.07
    )(__
    0.07
    ")]
↵
    0.07
    ующий
    0.07
    사랑
    0.06
     differed
    0.06
    	glColor
    0.06
    Activations Density 0.016%

    No Known Activations