© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 42795
    Prev
    Next
    INDEX
    Explanations

    life

    np_max-act · gemini-2.0-flash

    The neuron is triggered by occurrences of the word “lifeguard” (i.e. the token segments “lif” and “eguard”).

    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
    ิเว
    -0.07
    -exp
    -0.07
    .video
    -0.07
    _trajectory
    -0.06
    _topology
    -0.06
    φό
    -0.06
    adelphia
    -0.06
    xde
    -0.06
     realizado
    -0.06
    composition
    -0.06
    POSITIVE LOGITS
    	ast
    0.06
    程度
    0.06
     pricing
    0.06
    .positions
    0.06
    DDR
    0.06
    .setBackgroundResource
    0.06
     "\(
    0.06
    Programming
    0.06
    847
    0.06
    255
    0.06
    Activations Density 0.004%

    No Known Activations