© 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. 91206
    Prev
    Next
    INDEX
    Explanations

    Genus names

    np_max-act · gemini-2.0-flash

    This neuron detects the opening phrase of a taxonomic genus definition—i.e. the “[GenusName] is a genus of …” construction.

    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
    سين
    -0.07
     noreferrer
    -0.06
     nurs
    -0.06
    	pid
    -0.06
     varargin
    -0.06
    ゚
    -0.06
    apult
    -0.06
    .tabPage
    -0.06
    σιο
    -0.06
    VS
    -0.06
    POSITIVE LOGITS
    /sp
    0.07
     attentive
    0.07
    lobby
    0.06
    šli
    0.06
     residents
    0.06
     jeopard
    0.06
    奇
    0.06
    .Names
    0.06
     原
    0.06
    _ble
    0.06
    Activations Density 0.008%

    No Known Activations