© 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. 109802
    Prev
    Next
    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash

    This neuron fires on the literal period character used in version strings (e.g. the “.” in “1.0”) in XML/markup headers.

    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
    -Encoding
    -0.07
    byss
    -0.06
    _PHONE
    -0.06
    (work
    -0.06
    _ship
    -0.06
    StateToProps
    -0.06
    ‌پ
    -0.06
    -shopping
    -0.06
    Cake
    -0.06
    ////////////////////////////////////////////////////////////////
    -0.06
    POSITIVE LOGITS
    lení
    0.07
    itaire
    0.07
    	TokenNameIdentifier
    0.07
     Toni
    0.06
     Catalonia
    0.06
     определя
    0.06
     WindowManager
    0.06
     дж
    0.06
     voi
    0.06
    <TreeNode
    0.06
    Activations Density 0.001%

    No Known Activations