© 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. 31011
    Prev
    Next
    INDEX
    Explanations

    opener

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on single tokens naming tools, agents, or technical objects (e.g. “opener,” “fungicide,” “antibody”).

    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
    ACC
    -0.07
    简单
    -0.06
    PKG
    -0.06
     BODY
    -0.06
    ення
    -0.06
    _light
    -0.06
    510
    -0.06
    _taken
    -0.06
     noticeable
    -0.06
     chars
    -0.06
    POSITIVE LOGITS
     hobbies
    0.07
     Québec
    0.06
    .HandlerFunc
    0.06
     yytype
    0.06
    ]*
    0.06
     getObject
    0.06
     nex
    0.06
     BIOS
    0.06
    igInteger
    0.06
     lack
    0.06
    Activations Density 0.112%

    No Known Activations