© 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. 31061
    Prev
    Next
    INDEX
    Explanations

    personal experiences

    np_max-act · gemini-2.0-flash

    This neuron detects words and phrases that signal reminders or recollections (e.g. “reminder,” “every time,” “when … looked,” etc.), marking passages about remembering or being reminded.

    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
    pane
    -0.06
     Nancy
    -0.06
     sebou
    -0.06
     acclaimed
    -0.06
    ucks
    -0.06
    JC
    -0.06
    ABA
    -0.06
    AINS
    -0.06
     politically
    -0.05
    enerator
    -0.05
    POSITIVE LOGITS
    (_.
    0.07
     uom
    0.07
    월
    0.07
     ресур
    0.06
     Cv
    0.06
     Komment
    0.06
     ایران
    0.06
     Nikon
    0.06
     rumor
    0.06
    eddar
    0.06
    Activations Density 0.036%

    No Known Activations