© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 91525
    Prev
    Next
    INDEX
    Explanations

    academic research

    np_max-act · gemini-2.0-flash

    This neuron is strongly activated by common discourse-marker tokens (like “As,” “the,” “demand,” “continues,” etc.) that occur in transition or summary sentences—i.e. cues signaling topic shifts or forward-looking statements.

    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
     viral
    -0.06
     Reduction
    -0.06
     causing
    -0.06
     Pikachu
    -0.06
    Search
    -0.06
    _days
    -0.06
     since
    -0.06
     Alpha
    -0.06
     manageable
    -0.06
     reproduce
    -0.06
    POSITIVE LOGITS
     тв
    0.07
    oji
    0.06
     agricultural
    0.06
    	constructor
    0.06
    ↵↵    ↵
    0.06
    Liter
    0.06
     slept
    0.06
     Dire
    0.06
     nev
    0.06
    %D
    0.06
    Activations Density 0.020%

    No Known Activations