© 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
    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. 44425
    Prev
    Next
    INDEX
    Explanations

    oral

    np_max-act · gemini-2.0-flash

    The neuron lights up on explicit sexual‐act terms (for example “oral,” “sex,” “anal,” “fuck,” etc.).

    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
    CRYPT
    -0.07
    وقت
    -0.06
     paste
    -0.06
    decoder
    -0.06
    .discount
    -0.06
    concept
    -0.06
     Spurs
    -0.06
    TPL
    -0.06
     heavyweight
    -0.06
     лекар
    -0.06
    POSITIVE LOGITS
     Hawai
    0.07
    -commit
    0.07
    WillAppear
    0.07
     withholding
    0.06
    .apiUrl
    0.06
    .Navigator
    0.06
    نة
    0.06
     battered
    0.06
     із
    0.06
    .addListener
    0.06
    Activations Density 0.016%

    No Known Activations