© 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. 11-RESID-POST-AA
    6. 125923
    Prev
    Next
    INDEX
    Explanations

    drawing/plotting code

    np_max-act · gemini-2.0-flash

    This neuron detects calls to the Python Turtle graphics API (i.e. lines invoking turtle methods).

    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
     \$
    -0.07
     amb
    -0.07
    jump
    -0.06
     AIM
    -0.06
    COMPLETE
    -0.06
    �
    -0.06
     Elf
    -0.06
    AIM
    -0.06
     HEALTH
    -0.06
     Sanct
    -0.06
    POSITIVE LOGITS
     Identifier
    0.07
    .addData
    0.06
    reds
    0.06
     quarters
    0.06
    流量
    0.06
     정
    0.06
     hex
    0.06
    Preference
    0.06
    timestamps
    0.06
     monet
    0.06
    Activations Density 0.003%

    No Known Activations