© 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. 6599
    Prev
    Next
    INDEX
    Explanations

    storybook

    np_max-act · gemini-2.0-flash

    Python code snippets related to functionality and commands for running scripts or executing tasks in a web application context.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron is activated by mentions of the Gradio library (tokens like “gr,” “gradio,” “gr.Interface,” etc.).

    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
     exceptional
    -0.07
     DX
    -0.07
    ularity
    -0.07
     свеж
    -0.07
     itm
    -0.06
    vá
    -0.06
     때
    -0.06
     VERIFY
    -0.06
    _Master
    -0.06
     Pierre
    -0.06
    POSITIVE LOGITS
     setIs
    0.07
    charAt
    0.07
     انقلاب
    0.07
    학
    0.07
     geldi
    0.06
    _modified
    0.06
     mini
    0.06
    >S
    0.06
    isdigit
    0.06
     hair
    0.06
    Activations Density 0.001%

    No Known Activations