© 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. 9364
    Prev
    Next
    INDEX
    Explanations

    Affirmations

    np_max-act · gemini-2.0-flash

    The neuron detects occurrences of the root “affirm” (as in “affirm,” “affirmation,” “affirmations,” “mantra”) in self-affirming contexts.

    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
     workshop
    -0.06
     поб
    -0.06
    Lead
    -0.06
    	vo
    -0.06
    DBus
    -0.06
    管理
    -0.06
    .Progress
    -0.06
    DBG
    -0.06
     polarity
    -0.06
     Theresa
    -0.05
    POSITIVE LOGITS
     ####
    0.07
    ;;;;
    0.07
     六
    0.06
     empty
    0.06
    _INCREF
    0.06
     completionHandler
    0.06
     Tik
    0.06
    folk
    0.06
    เสร
    0.06
     mě
    0.06
    Activations Density 0.016%

    No Known Activations