© 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. 110242
    Prev
    Next
    INDEX
    Explanations

    sem

    np_max-act · gemini-2.0-flash

    The neuron is tuned to detect occurrences of the disease name “thalassemia” (and its subword parts).

    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
     سوال
    -0.07
    emons
    -0.06
     nhờ
    -0.06
    Vs
    -0.06
    结合
    -0.06
     Perspective
    -0.06
     METHODS
    -0.06
    駐
    -0.06
     nga
    -0.06
     ============================================================================↵
    -0.06
    POSITIVE LOGITS
    zá
    0.06
    .Priority
    0.06
     Thermal
    0.06
    'H
    0.06
     Broad
    0.06
     듣
    0.06
    sound
    0.06
     쉬
    0.06
    slots
    0.06
     scoped
    0.06
    Activations Density 0.001%

    No Known Activations