© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 6953
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    The neuron is specialized to detect mentions of physical relocation—i.e. occurrences of “move,” “moved,” “relocated,” and similar.

    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
    ../../../../
    -0.07
     respond
    -0.07
     Rin
    -0.07
    	up
    -0.06
    (results
    -0.06
    ({
    -0.06
    دن
    -0.06
    Look
    -0.06
     amounts
    -0.06
     ден
    -0.06
    POSITIVE LOGITS
     ideologies
    0.07
     PIL
    0.07
    mask
    0.07
    _FOCUS
    0.06
    jev
    0.06
    лер
    0.06
    зі
    0.06
    พย
    0.06
     Wass
    0.06
    _MANAGER
    0.06
    Activations Density 0.048%

    No Known Activations