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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 80587
    Prev
    Next
    INDEX
    Explanations

    closer

    np_max-act · gemini-2.0-flash

    explicit sexual scenarios involving explicit consent and dynamics between characters.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires on phrases that describe the speaker drawing “you” into intimate physical closeness with “me.”

    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
    belt
    -0.07
    gate
    -0.07
    -------↵↵
    -0.06
    tığı
    -0.06
    -funded
    -0.06
    .Before
    -0.06
     Ά
    -0.06
    Clin
    -0.06
     detta
    -0.06
    .off
    -0.06
    POSITIVE LOGITS
     Searching
    0.07
     приблиз
    0.07
    .Contact
    0.07
    creative
    0.07
    运
    0.06
     غر
    0.06
    queeze
    0.06
     sticks
    0.06
     클래스
    0.06
     clarify
    0.06
    Activations Density 0.008%

    No Known Activations