© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 89083
    Prev
    Next
    INDEX
    Explanations

    will would

    np_max-act · gemini-2.0-flash

    This neuron detects modal auxiliary constructions signaling future or conditional actions, such as “will …” or “would ….”

    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
     arb
    -0.07
    Builders
    -0.07
     skew
    -0.06
    _flush
    -0.06
    Salvar
    -0.06
    _ans
    -0.06
     Cs
    -0.06
     nhằm
    -0.06
    -cn
    -0.06
    ,address
    -0.06
    POSITIVE LOGITS
     UN
    0.07
     Portrait
    0.07
     mold
    0.06
    �n
    0.06
     psik
    0.06
     hvordan
    0.06
    í
    0.06
    	il
    0.06
     outputStream
    0.06
     marvel
    0.06
    Activations Density 0.034%

    No Known Activations