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. 12860
    Prev
    Next
    INDEX
    Explanations

    erotica

    np_max-act · gemini-2.0-flash

    This neuron is primarily triggered by erotic content—words referring to intimate body parts and sexual 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
    sku
    -0.07
    020
    -0.06
     hé
    -0.06
     festival
    -0.06
    -cn
    -0.06
    061
    -0.06
    joint
    -0.06
     joined
    -0.06
    _agg
    -0.06
    achten
    -0.06
    POSITIVE LOGITS
    Conditional
    0.06
    _LOG
    0.06
     jíd
    0.06
    .QRect
    0.06
     сильно
    0.06
     CallingConvention
    0.06
    .addItem
    0.06
     Nursing
    0.06
    mploy
    0.05
     umožňuje
    0.05
    Activations Density 0.010%

    No Known Activations