© 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. 11-RESID-POST-AA
    6. 54018
    Prev
    Next
    INDEX
    Explanations

    programming and technology

    np_max-act · gemini-2.0-flash

    This neuron detects code or discussion about programmatically scrolling an element (often its next sibling) into view (e.g. using scrollIntoView or related scrolling logic).

    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
    gui
    -0.07
    ασίας
    -0.07
    nějších
    -0.06
    _PI
    -0.06
    )];↵↵
    -0.06
    -su
    -0.06
    さま
    -0.06
    主义
    -0.06
     Vec
    -0.06
    -this
    -0.06
    POSITIVE LOGITS
    labels
    0.06
     Voices
    0.06
     out
    0.06
    -axis
    0.06
    <tag
    0.06
    *=*=
    0.06
     Bar
    0.06
    κος
    0.06
    -thirds
    0.06
     발매
    0.06
    Activations Density 0.393%

    No Known Activations