© 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. 9376
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    This neuron detects conditional language patterns—phrases expressing “if/when… then…” or obligations (e.g. “if X happens, you have to Y”).

    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
    арі
    -0.07
    orgia
    -0.07
     Paths
    -0.06
    	req
    -0.06
    -written
    -0.06
     threatened
    -0.06
    (regex
    -0.06
     Ông
    -0.06
     citation
    -0.06
     cabinet
    -0.06
    POSITIVE LOGITS
     treffen
    0.06
    -fontawesome
    0.06
     무슨
    0.06
    _mult
    0.06
     لل
    0.06
     prev
    0.06
     Exxon
    0.06
     einf
    0.06
    villa
    0.06
     Holden
    0.06
    Activations Density 0.063%

    No Known Activations