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. 90044
    Prev
    Next
    INDEX
    Explanations

    Internet scraped text

    np_max-act · gemini-2.0-flash

    The neuron activates on placeholder name tokens (e.g. “NAME_1”).

    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
     banners
    -0.07
    ลาย
    -0.06
    ROUT
    -0.06
    Founder
    -0.06
     dnes
    -0.06
     tabi
    -0.06
     \"%
    -0.06
    -vector
    -0.06
    -mon
    -0.06
     العراق
    -0.06
    POSITIVE LOGITS
     IT
    0.06
    chema
    0.06
    nette
    0.06
     dumpster
    0.06
    living
    0.06
     Valle
    0.06
    -directory
    0.05
    rieve
    0.05
    configured
    0.05
     Saw
    0.05
    Activations Density 0.099%

    No Known Activations