© 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. 12977
    Prev
    Next
    INDEX
    Explanations

    town or city

    np_max-act · gemini-2.0-flash

    The neuron activates on words denoting a municipality (e.g. “city,” “Stadt,” “town”).

    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
     dikkate
    -0.07
    仅
    -0.07
    otland
    -0.06
     shotgun
    -0.06
     miner
    -0.06
    <!--
    -0.06
     روستا
    -0.06
     procure
    -0.06
     Kidd
    -0.06
    καν
    -0.06
    POSITIVE LOGITS
     stuffed
    0.07
    イク
    0.07
     oversized
    0.06
     evening
    0.06
     adipiscing
    0.06
     behind
    0.06
     apresent
    0.06
     seasons
    0.06
     إ
    0.06
    unlink
    0.06
    Activations Density 0.024%

    No Known Activations