© 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. 12373
    Prev
    Next
    INDEX
    Explanations

    Recent

    np_max-act · gemini-2.0-flash

    The neuron is triggered by the word “Recent” when used as a section heading or label at the start of a text block.

    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
     Butterfly
    -0.08
     yür
    -0.07
     HOL
    -0.07
     Booth
    -0.07
     mort
    -0.07
    Hyper
    -0.07
     thrott
    -0.07
     männer
    -0.07
     وظ
    -0.07
     Dir
    -0.06
    POSITIVE LOGITS
     recent
    0.16
     recently
    0.14
    Recent
    0.11
    recent
    0.11
     Recent
    0.11
     Recently
    0.10
    最近
    0.10
     최근
    0.08
     gần
    0.08
    _recent
    0.08
    Activations Density 0.022%

    No Known Activations