© 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. 129585
    Prev
    Next
    INDEX
    Explanations

    location

    np_max-act · gemini-2.0-flash

    This neuron detects locational prepositions (especially “at” and “in”) that mark where something or someone is.

    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
    Speech
    -0.07
    。。
    -0.07
    Flash
    -0.06
     correct
    -0.06
    123
    -0.06
     Pager
    -0.06
    стер
    -0.06
    (draw
    -0.06
     scouts
    -0.06
    connect
    -0.06
    POSITIVE LOGITS
     sağlıklı
    0.07
     застосов
    0.07
    キュ
    0.06
    %C
    0.06
    ğinin
    0.06
    _UNS
    0.06
    .Enable
    0.06
     사건
    0.06
    شاه
    0.06
    WillAppear
    0.06
    Activations Density 0.022%

    No Known Activations