© 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. 91431
    Prev
    Next
    INDEX
    Explanations

    questions/discussions

    np_max-act · gemini-2.0-flash

    This neuron activates on tokens within detailed, step-by-step explanatory or elimination reasoning sections of the assistant’s answers.

    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
     isc
    -0.07
     rop
    -0.07
     exam
    -0.07
    ワ
    -0.06
    isse
    -0.06
    .gwt
    -0.06
     Pandora
    -0.06
     addObserver
    -0.06
    airro
    -0.06
     losses
    -0.06
    POSITIVE LOGITS
    -interface
    0.08
    >You
    0.06
    การท
    0.06
    ?>/
    0.06
    +m
    0.06
    ۱۵
    0.06
     ~
    0.06
    //
↵
    0.06
    //--------------------------------------------------------------------------------
    0.06
    จะต
    0.06
    Activations Density 0.030%

    No Known Activations