© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 55374
    Prev
    Next
    INDEX
    Explanations

    api

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of APIs and related technical interface terms (e.g. “API,” “REST,” “JSON,” “XML,” “feed,” “via the API”).

    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
    ARB
    -0.08
     Bol
    -0.07
    ЙЙ
    -0.06
     Corp
    -0.06
    pure
    -0.06
    hi
    -0.06
    _my
    -0.06
    Address
    -0.06
    _BP
    -0.06
     Bal
    -0.06
    POSITIVE LOGITS
     إلا
    0.06
    نسا
    0.06
     emo
    0.06
    inář
    0.06
    'd
    0.06
     winnings
    0.06
     franch
    0.06
    toArray
    0.06
     إليه
    0.06
     valor
    0.06
    Activations Density 0.024%

    No Known Activations