© 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. 68678
    Prev
    Next
    INDEX
    Explanations

    personal

    np_max-act · gemini-2.0-flash

    The neuron fires on words listing prohibited comment‐section content—e.g. terms like “personal,” “attacks,” “inappropriate,” “offensive,” “hate speech,” etc.

    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
     feats
    -0.07
     forced
    -0.07
     vending
    -0.06
    BA
    -0.06
     samp
    -0.06
     hone
    -0.06
    ugen
    -0.06
    ционные
    -0.06
     Bak
    -0.06
     Mann
    -0.06
    POSITIVE LOGITS
    (def
    0.07
     në
    0.06
     FOUND
    0.06
     {}↵↵↵
    0.06
    FolderPath
    0.06
     mourn
    0.06
    -trigger
    0.06
    Việc
    0.06
    (de
    0.06
     NSCoder
    0.06
    Activations Density 0.011%

    No Known Activations