© 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. 7941
    Prev
    Next
    INDEX
    Explanations

    Structured lists

    np_max-act · gemini-2.0-flash

    This neuron activates on tokens naming quantitative metadata fields (like population, ISO code, land area, website, rating, revenue, etc.).

    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
    Pager
    -0.07
    реп
    -0.06
     mexico
    -0.06
    Calibri
    -0.06
     [];
↵
    -0.06
     Officials
    -0.06
     ÜNİVERSİTESİ
    -0.06
     rad
    -0.06
    _binary
    -0.06
    				↵				↵
    -0.06
    POSITIVE LOGITS
    巡
    0.07
    )__
    0.07
     tạm
    0.07
    Without
    0.06
     Seks
    0.06
    _AHB
    0.06
     prům
    0.06
    HC
    0.06
     disfr
    0.06
     applicationContext
    0.06
    Activations Density 0.029%

    No Known Activations