© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 7821
    Prev
    Next
    INDEX
    Explanations

    anal

    np_max-act · gemini-2.0-flash

    This neuron detects explicit mentions of anal sexual activity.

    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
    .Resources
    -0.07
    .fe
    -0.06
     Wade
    -0.06
    auction
    -0.06
    Pdf
    -0.06
     hdc
    -0.06
    	fields
    -0.06
     detriment
    -0.06
    cích
    -0.06
     salida
    -0.06
    POSITIVE LOGITS
     trump
    0.06
     şiş
    0.06
    qrst
    0.06
     bluetooth
    0.06
     Bluetooth
    0.06
    ];↵
    0.06
     avg
    0.06
    	const
    0.06
    -third
    0.06
     ø
    0.06
    Activations Density 0.007%

    No Known Activations