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. 30376
    Prev
    Next
    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash

    The neuron fires on explicit mentions or descriptions of intimate body parts—especially genitalia—marking when the text is detailing or focusing on those regions.

    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
    PERT
    -0.07
     MOUSE
    -0.07
     Hermes
    -0.07
     swift
    -0.07
    岁
    -0.07
     contempl
    -0.06
    宗
    -0.06
     Valk
    -0.06
     curse
    -0.06
     perpetrators
    -0.06
    POSITIVE LOGITS
     towns
    0.06
    _UNKNOWN
    0.06
     якого
    0.06
     Relative
    0.06
    objc
    0.06
    >Loading
    0.06
    ż
    0.06
    =n
    0.05
    >n
    0.05
    rysler
    0.05
    Activations Density 0.079%

    No Known Activations