© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 57111
    Prev
    Next
    INDEX
    Explanations

    Chemical reaction mechanisms

    np_max-act · gemini-2.0-flash

    The neuron fires on formal technical terms describing chemical or kinetic processes (e.g. “mechanism,” “kinetics,” “reaction,” “proceed,” etc.), indicating it’s detecting discussion of reaction mechanisms and rates.

    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
    Guild
    -0.07
    ang
    -0.07
    Clark
    -0.06
    Tim
    -0.06
    석
    -0.06
    ANG
    -0.06
     Katz
    -0.06
    Domain
    -0.06
     project
    -0.06
     TZ
    -0.06
    POSITIVE LOGITS
    @register
    0.07
    북도
    0.07
    dığında
    0.07
    annels
    0.06
     بنابراین
    0.06
    ocytes
    0.06
    _direct
    0.06
     mayoría
    0.06
     getSupportActionBar
    0.06
    irma
    0.06
    Activations Density 0.066%

    No Known Activations