© 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. 110255
    Prev
    Next
    INDEX
    Explanations

    Prepositions and auxiliary verbs

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on the phrase “filled with.”

    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
    하신
    -0.07
    _TI
    -0.07
     din
    -0.07
    leyen
    -0.06
     testName
    -0.06
    848
    -0.06
    じゃない
    -0.06
    ']/
    -0.06
     SOCK
    -0.06
    _DEFINITION
    -0.06
    POSITIVE LOGITS
    alan
    0.07
     �
    0.06
     bolster
    0.06
    اف
    0.06
    etag
    0.06
     colle
    0.06
     ميل
    0.06
    ội
    0.05
    TURE
    0.05
    �回
    0.05
    Activations Density 0.232%

    No Known Activations