© 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. 126372
    Prev
    Next
    INDEX
    Explanations

    life

    np_max-act · gemini-2.0-flash

    This neuron activates on explicit references to sex toys or other sexual devices.

    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
    art
    -0.07
     gol
    -0.07
    urse
    -0.07
    Utility
    -0.07
     prefetch
    -0.07
     suites
    -0.06
    elere
    -0.06
    WRITE
    -0.06
     Now
    -0.06
    posed
    -0.06
    POSITIVE LOGITS
     번째
    0.06
    ><?=$
    0.06
     운동
    0.06
    .asp
    0.06
     ___
    0.06
    €↵
    0.06
    การส
    0.06
    nl
    0.06
     cít
    0.06
    /copyleft
    0.06
    Activations Density 0.048%

    No Known Activations