Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 90528
    Prev
    Next
    INDEX
    Explanations

    legal and bureaucratic matters

    np_max-act · gemini-2.0-flash

    This neuron primarily activates on the word “this.”

    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
    .Driver
    -0.07
    CK
    -0.06
     Fine
    -0.06
    	bs
    -0.06
    en
    -0.06
    .vn
    -0.06
    -names
    -0.06
    USTER
    -0.06
     Charter
    -0.06
     Shrine
    -0.06
    POSITIVE LOGITS
    =output
    0.07
    .articles
    0.07
     arity
    0.06
    flatten
    0.06
     živ
    0.06
    ());//
    0.06
    ]={
    0.06
    orientation
    0.06
    писание
    0.06
    ]=$
    0.06
    Activations Density 0.063%

    No Known Activations