Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 84747
    Prev
    Next
    INDEX
    Explanations

    relationship hints/signals

    np_max-act · gemini-2.0-flash

    The neuron fires on words and phrases signaling flirtatious or submissive sexual behavior (e.g., flirt, hints, submissiveness).

    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
     foot
    -0.07
     calcium
    -0.06
     delegate
    -0.06
     received
    -0.06
     rigorous
    -0.06
    cip
    -0.06
     event
    -0.06
    -mar
    -0.06
    atos
    -0.06
    udder
    -0.05
    POSITIVE LOGITS
    انگلیسی
    0.07
     zách
    0.07
     تجهیزات
    0.07
    Uint
    0.06
    �
    0.06
     答
    0.06
    Fab
    0.06
     bacheca
    0.06
     Stellar
    0.06
    跌
    0.06
    Activations Density 0.037%

    No Known Activations