© 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. 91410
    Prev
    Next
    INDEX
    Explanations

    Actions

    np_max-act · gemini-2.0-flash

    The neuron fires on verbs and verb forms that issue user-actions or commands (e.g. block, ban, use, disable, limit) indicating instructions or directives.

    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
     Kate
    -0.06
    	board
    -0.06
     Canon
    -0.06
     Laure
    -0.06
     Juice
    -0.06
    raphics
    -0.06
    γ
    -0.06
    izons
    -0.06
    _restrict
    -0.06
    flux
    -0.06
    POSITIVE LOGITS
     were
    0.07
     bell
    0.07
     experimenting
    0.06
    CppMethodIntialized
    0.06
    	echo
    0.06
     LAST
    0.06
    、い
    0.06
    andles
    0.06
    _HIDDEN
    0.06
    ButtonItem
    0.06
    Activations Density 0.065%

    No Known Activations