© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 41520
    Prev
    Next
    INDEX
    Explanations

    Archives

    np_max-act · gemini-2.0-flash

    The neuron fires on the little blog‐UI header labels and metadata markers (e.g. “Tag,” “Archives,” “Menu/Monthly,” and the following colon).

    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
     citiz
    -0.08
    วด
    -0.07
     ainsi
    -0.06
     Çalış
    -0.06
    (buffer
    -0.06
     элем
    -0.06
     проз
    -0.06
    §ط
    -0.06
    .keyboard
    -0.06
     オ
    -0.06
    POSITIVE LOGITS
     Howell
    0.06
    itemName
    0.06
     postseason
    0.06
     emoji
    0.06
     відбувається
    0.06
     podařilo
    0.06
     economist
    0.06
    ashire
    0.06
     condos
    0.06
     revered
    0.06
    Activations Density 0.004%

    No Known Activations