© 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. 13398
    Prev
    Next
    INDEX
    Explanations

    English

    np_max-act · gemini-2.0-flash

    The neuron specifically detects mentions of the English language (e.g. the token “English”).

    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
    _tool
    -0.07
     partition
    -0.07
    a
    -0.07
     saldırı
    -0.07
    "a
    -0.07
    aud
    -0.07
    ropoda
    -0.07
     zone
    -0.07
     Sai
    -0.07
    xaa
    -0.07
    POSITIVE LOGITS
     English
    0.14
    English
    0.10
     англ
    0.08
     Anglo
    0.08
     ginger
    0.07
     Gentle
    0.07
     انگلیسی
    0.07
     anglais
    0.07
    tığı
    0.07
     english
    0.07
    Activations Density 0.020%

    No Known Activations