Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 55746
    Prev
    Next
    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash

    This neuron activates on discourse markers that introduce a summary or conclusion (e.g., “Overall,”).

    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
     Cue
    -0.07
    Cached
    -0.07
     représent
    -0.07
     nuova
    -0.06
    $category
    -0.06
     playable
    -0.06
    (Collections
    -0.06
    Developer
    -0.06
    �
    -0.06
     Iter
    -0.06
    POSITIVE LOGITS
     onze
    0.07
     rozp
    0.06
     pornost
    0.06
    /edit
    0.06
    ,message
    0.06
     yine
    0.06
     Gina
    0.06
    webElementX
    0.06
    	widget
    0.06
    ализ
    0.06
    Activations Density 0.023%

    No Known Activations