© 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. 91379
    Prev
    Next
    INDEX
    Explanations

    moderators

    np_max-act · gemini-2.0-flash

    The neuron fires on content‐moderation warning text—particularly on fragments of the word “moderation” in the “YOUR INPUT VIOLATES OUR CONTENT MODERATION GUIDELINES” message.

    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
    uste
    -0.07
    xaf
    -0.06
    ến
    -0.06
    らし
    -0.06
     ultimately
    -0.06
    .shapes
    -0.06
     Leah
    -0.06
    らい
    -0.06
     trabaj
    -0.06
    meyi
    -0.06
    POSITIVE LOGITS
     इ
    0.07
    ($(
    0.07
     sectarian
    0.06
    ,'
    0.06
     witnessed
    0.06
     vowed
    0.06
     demo
    0.06
     Fucking
    0.06
    	case
    0.06
    .ImageIcon
    0.06
    Activations Density 0.001%

    No Known Activations