© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 41165
    Prev
    Next
    INDEX
    Explanations

    eric

    np_max-act · gemini-2.0-flash

    The neuron fires on specialized, domain-specific terms (e.g. mechanical parts like “rotor” or “stator,” engineering jargon such as “elastomeric,” and code identifiers like the class name “B”).

    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
    _multi
    -0.06
     vez
    -0.06
     regress
    -0.06
     предназнач
    -0.06
    /question
    -0.06
    über
    -0.06
    _mas
    -0.06
     repos
    -0.06
     Instructions
    -0.06
     culpa
    -0.06
    POSITIVE LOGITS
    虚
    0.07
    MH
    0.07
     havoc
    0.07
     session
    0.06
        		
    0.06
    солют
    0.06
    (boolean
    0.06
    )},↵
    0.06
     Intelligence
    0.06
     Appeals
    0.06
    Activations Density 0.492%

    No Known Activations