© 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. 12594
    Prev
    Next
    INDEX
    Explanations

    physics, science

    np_max-act · gemini-2.0-flash

    The neuron responds to specialized physics and mathematics terminology—i.e. advanced technical terms from fundamental physics.

    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
    Subviews
    -0.06
    utf
    -0.06
     busy
    -0.06
     report
    -0.06
    .Open
    -0.06
    _struct
    -0.06
     sidewalks
    -0.06
    乘
    -0.06
    (item
    -0.06
    ouncing
    -0.06
    POSITIVE LOGITS
    เกษ
    0.07
    .complete
    0.06
     kapsam
    0.06
     basename
    0.06
    urchase
    0.06
    -independent
    0.06
    .Xna
    0.06
     kilomet
    0.06
     consenting
    0.06
     جا
    0.06
    Activations Density 0.047%

    No Known Activations