© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 41365
    Prev
    Next
    INDEX
    Explanations

    time prepositions

    np_max-act · gemini-2.0-flash

    The neuron detects temporal sequence cue phrases (like “after,” “only after,” “only at,” “it was not until”) that signal one event following or depending on another.

    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
    	className
    -0.06
    _cart
    -0.06
    _kernel
    -0.06
    monitor
    -0.06
     anxious
    -0.06
     участ
    -0.06
     rect
    -0.06
     subsets
    -0.06
     eliminating
    -0.06
    .PARAM
    -0.06
    POSITIVE LOGITS
     Comparable
    0.07
    ате
    0.06
    辦
    0.06
     rozp
    0.06
    UGC
    0.06
     sessionFactory
    0.06
    仕事
    0.06
    游戏
    0.06
     roky
    0.06
    oteric
    0.06
    Activations Density 0.012%

    No Known Activations