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. 40518
    Prev
    Next
    INDEX
    Explanations

    family members

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of family relationship terms (e.g., “son,” “brother,” “sister”).

    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
    atis
    -0.07
     McMahon
    -0.07
    質
    -0.07
     Tyto
    -0.06
    eza
    -0.06
    .rabbit
    -0.06
     crab
    -0.06
    ippo
    -0.06
     racially
    -0.06
    ès
    -0.06
    POSITIVE LOGITS
    \widgets
    0.08
    origin
    0.07
     queryInterface
    0.06
    .labels
    0.06
     temporary
    0.06
     Broadcasting
    0.06
    CALE
    0.06
    
    0.06
     safeg
    0.06
     wirk
    0.06
    Activations Density 0.008%

    No Known Activations