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. 90459
    Prev
    Next
    INDEX
    Explanations

    adverbs

    np_max-act · gemini-2.0-flash

    This neuron fires on adverbs ending in “-ally.”

    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
    My
    -0.07
    规
    -0.07
     avail
    -0.07
     refine
    -0.07
     Improved
    -0.07
     My
    -0.06
     irritation
    -0.06
    呼ば
    -0.06
     Awakening
    -0.06
    以及
    -0.06
    POSITIVE LOGITS
     meis
    0.07
    _Write
    0.06
    Inicio
    0.06
     verbally
    0.06
     Zukunft
    0.06
    -dismiss
    0.06
    _FINISH
    0.06
    ubre
    0.06
    	Class
    0.06
     España
    0.06
    Activations Density 0.106%

    No Known Activations