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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 127037
    Prev
    Next
    INDEX
    Explanations

    around

    np_max-act · gemini-2.0-flash

    explicit descriptions of intimate sexual scenarios.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects words and phrases that describe intimate physical closeness, such as embracing, wrapping arms around, pulling someone close, and similar touch-oriented actions.

    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
    bum
    -0.06
    _ads
    -0.06
    -security
    -0.06
     shiny
    -0.06
    .numpy
    -0.06
    .Flags
    -0.06
     switches
    -0.06
     setLoading
    -0.06
    vars
    -0.06
    edula
    -0.05
    POSITIVE LOGITS
    akeup
    0.07
     보기
    0.07
    σματα
    0.07
    .MainActivity
    0.07
    riter
    0.06
     اروپا
    0.06
    .den
    0.06
     exercising
    0.06
     различ
    0.06
     今
    0.06
    Activations Density 0.010%

    No Known Activations