© 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. 54129
    Prev
    Next
    INDEX
    Explanations

    sleep

    np_max-act · gemini-2.0-flash

    The neuron fires on gentle, comforting or sleep‐related words and phrases (e.g. “quiet,” “peaceful,” “relax,” “rest,” “sweet dreams”).

    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
    .parse
    -0.06
    _transport
    -0.06
    athroom
    -0.06
     Sự
    -0.06
    	
    ↵
    -0.06
    _BROWSER
    -0.06
     svém
    -0.06
    .SP
    -0.06
    verbosity
    -0.05
    DIR
    -0.05
    POSITIVE LOGITS
    ьют
    0.07
    ceive
    0.07
     Assuming
    0.06
     outward
    0.06
     recib
    0.06
     Marker
    0.06
     Ill
    0.06
    õi
    0.06
    )):
    0.06
    장이
    0.06
    Activations Density 0.006%

    No Known Activations