© 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. 92287
    Prev
    Next
    INDEX
    Explanations

    oh

    np_max-act · gemini-2.0-flash

    The neuron activates on chemical compound names that include numbered locants (e.g. “1,2,3-propanetricarboxylic acid”).

    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
     tienes
    -0.07
    942
    -0.06
    arResult
    -0.06
    _videos
    -0.06
    .two
    -0.06
    โจ
    -0.06
    мотря
    -0.06
    Border
    -0.06
     hd
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     sürekli
    0.08
    icrous
    0.07
    ุ
    0.06
    .Port
    0.06
     verifies
    0.06
    盤
    0.06
    ้าห
    0.06
     chant
    0.06
     getToken
    0.06
    apı
    0.06
    Activations Density 0.146%

    No Known Activations