© 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. 126797
    Prev
    Next
    INDEX
    Explanations

    chemical compounds

    np_max-act · gemini-2.0-flash

    The neuron detects occurrences of the substring “pyridine” (and its split‐up tokens) in chemical compound names.

    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
    _close
    -0.07
     Stuart
    -0.07
    Marshal
    -0.07
    (HaveOccurred
    -0.07
    Common
    -0.07
     Generally
    -0.07
     gramm
    -0.06
     Neck
    -0.06
    lec
    -0.06
    pper
    -0.06
    POSITIVE LOGITS
     Opportunity
    0.06
     ici
    0.06
    。。
    0.06
    .webdriver
    0.06
    ød
    0.06
     Επ
    0.06
    isu
    0.06
    Ú
    0.06
    .Constant
    0.06
     उसस
    0.06
    Activations Density 0.041%

    No Known Activations