© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 6963
    Prev
    Next
    INDEX
    Explanations

    Updates/edits in technical contexts

    np_max-act · gemini-2.0-flash

    This neuron detects section‐heading tokens that mark edits or answer sections (e.g. “Update,” “Edit,” “A:”).

    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
     начина
    -0.07
     arrests
    -0.06
     leaps
    -0.06
     extensions
    -0.06
     Extensions
    -0.06
     Cards
    -0.06
    _DETECT
    -0.06
     Southampton
    -0.06
     olsun
    -0.06
    PlainText
    -0.06
    POSITIVE LOGITS
    $rows
    0.07
     noh
    0.06
    responseObject
    0.06
     лей
    0.06
    ));↵
    0.06
     dataSource
    0.06
    DIC
    0.06
     T
    0.06
     Setter
    0.06
    )):
↵
    0.06
    Activations Density 0.024%

    No Known Activations