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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 109816
    Prev
    Next
    INDEX
    Explanations

    chat logs

    np_max-act · gemini-2.0-flash

    The neuron fires on the numeric or “NAME_x” tokens used as speaker or character identifiers in the chat.

    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
     установлен
    -0.06
     world
    -0.06
     tand
    -0.06
    _OWNER
    -0.06
    -ag
    -0.06
     gold
    -0.06
    -अ
    -0.06
    _BUTTON
    -0.06
    -face
    -0.06
    /St
    -0.06
    POSITIVE LOGITS
     ey
    0.06
     Interestingly
    0.06
    となり
    0.06
     Daemon
    0.06
     рабоч
    0.06
     зелен
    0.06
     horsepower
    0.06
     collapsing
    0.06
    packing
    0.06
    fillType
    0.06
    Activations Density 0.012%

    No Known Activations