© 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. 41670
    Prev
    Next
    INDEX
    Explanations

    sudden feelings

    np_max-act · gemini-2.0-flash

    The neuron fires on tokens that describe a character’s internal emotional or physical state (e.g. “surge,” “relief,” “pride,” “wash” in the context of feelings).

    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
     burada
    -0.08
    furt
    -0.07
    ?(:
    -0.07
     gelmiş
    -0.07
     σε
    -0.06
    真是
    -0.06
    ился
    -0.06
    _CONVERT
    -0.06
    isclosed
    -0.06
    zoom
    -0.06
    POSITIVE LOGITS
    атки
    0.07
     Rath
    0.07
    ルド
    0.07
    732
    0.07
     revis
    0.06
    _MODULE
    0.06
    Regarding
    0.06
    ,并
    0.06
     pige
    0.06
    ерап
    0.06
    Activations Density 0.005%

    No Known Activations