© 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. 126277
    Prev
    Next
    INDEX
    Explanations

    The neuron is highly sensitive to explicit mentions or descriptions of incestuous sexual content.

    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
    ProgressHUD
    -0.07
     silently
    -0.06
    库
    -0.06
    .dict
    -0.06
     Uruguay
    -0.06
    龍
    -0.06
     Vương
    -0.06
     끝
    -0.06
     horr
    -0.06
     registrar
    -0.06
    POSITIVE LOGITS
     incest
    0.09
    (Messages
    0.07
     expos
    0.07
     inh
    0.06
    Override
    0.06
     {{--<
    0.06
    ?>>↵
    0.06
    (parseInt
    0.06
    nish
    0.06
    ><?=$
    0.06
    Activations Density 0.002%

    No Known Activations