© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 110146
    Prev
    Next
    INDEX
    Explanations

    amount or exposure

    np_max-act · gemini-2.0-flash

    The neuron fires on descriptions emphasizing how scant or revealing an outfit is—phrases that something “leaves little to the imagination.”

    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
    OUND
    -0.06
    �
    -0.06
    文化
    -0.06
    -out
    -0.06
     şek
    -0.06
     head
    -0.06
    GeneratedValue
    -0.06
    _BOOK
    -0.06
    _FRE
    -0.06
    女
    -0.06
    POSITIVE LOGITS
     Bs
    0.07
    (strpos
    0.06
    сі
    0.06
     Oversight
    0.06
    有点
    0.06
     सकत
    0.06
     ISBN
    0.06
    _hresult
    0.06
     많은
    0.06
     JIT
    0.06
    Activations Density 0.002%

    No Known Activations