© 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. 8921
    Prev
    Next
    INDEX
    Explanations

    Web scraping

    np_max-act · gemini-2.0-flash

    This neuron responds to words and phrases used in definitional or descriptive sentences (e.g. “is a…,” “It consists of…,” “was published…”) that introduce or explain a piece of media.

    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
    _visibility
    -0.06
     Late
    -0.06
     unknown
    -0.06
     光
    -0.06
     Vit
    -0.06
    FR
    -0.06
    ivered
    -0.06
     практически
    -0.06
    antium
    -0.06
    ootball
    -0.05
    POSITIVE LOGITS
     Query
    0.07
    正在
    0.07
    	templateUrl
    0.06
    -ra
    0.06
    =\"#
    0.06
     xmlhttp
    0.06
    ">&#
    0.06
    .piece
    0.06
     swapped
    0.06
    bsub
    0.06
    Activations Density 0.135%

    No Known Activations