Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 126512
    Prev
    Next
    INDEX
    Explanations

    text excerpts

    np_max-act · gemini-2.0-flash

    The neuron mainly lights up on common English function words—especially short prepositions and articles (“in,” “the,” “for,” “when,” etc.)—marking the connective scaffolding of sentences.

    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
     sometimes
    -0.06
    iples
    -0.06
    igr
    -0.06
    646
    -0.06
    캐
    -0.06
    (Max
    -0.06
     notebooks
    -0.06
     initiation
    -0.05
    byt
    -0.05
    浪
    -0.05
    POSITIVE LOGITS
     hodnoty
    0.07
     đích
    0.07
    	Start
    0.07
     dim
    0.06
     roman
    0.06
    ierten
    0.06
     producto
    0.06
    按钮
    0.06
     camb
    0.06
    -bars
    0.06
    Activations Density 0.111%

    No Known Activations