© 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. 30637
    Prev
    Next
    INDEX
    Explanations

    lab analysis

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of laboratory molecular‐genetic typing and analysis methods (e.g. restriction endonuclease analysis, PFGE, pulsed-field gel electrophoresis, sequencing).

    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
     buzzing
    -0.07
     flip
    -0.07
    -most
    -0.06
    ino
    -0.06
    Christ
    -0.06
     rospy
    -0.06
    atives
    -0.06
    utting
    -0.06
    ube
    -0.06
    iates
    -0.06
    POSITIVE LOGITS
     облі
    0.07
     UserName
    0.07
     BaseController
    0.06
     Proble
    0.06
    _resolution
    0.06
     을
    0.06
     nhạc
    0.06
     особенно
    0.06
     kèo
    0.06
     الشركة
    0.06
    Activations Density 0.013%

    No Known Activations