© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 56505
    Prev
    Next
    INDEX
    Explanations

    quotes/sayings

    np_max-act · gemini-2.0-flash

    The neuron responds to words that mark personal anecdotes or reported speech—especially first‐person recollection verbs like “said,” “remembered,” and “writes.”

    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
    -digit
    -0.07
     antib
    -0.07
    MODE
    -0.07
    _alloc
    -0.06
    än
    -0.06
    ngoing
    -0.06
    EdgeInsets
    -0.06
     budding
    -0.06
    島
    -0.06
    ]),↵
    -0.06
    POSITIVE LOGITS
    UpEdit
    0.07
    เมตร
    0.07
     milfs
    0.06
     elem
    0.06
     DIST
    0.06
     Richie
    0.06
    (tree
    0.06
    _future
    0.06
     çıktı
    0.06
    ्थन
    0.06
    Activations Density 0.070%

    No Known Activations