© 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. 73933
    Prev
    Next
    INDEX
    Explanations

    Software/Operating Systems

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect mentions of software and platform names (e.g. operating systems, databases, and related technologies).

    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
    _gr
    -0.07
     Them
    -0.06
    _ENT
    -0.06
     trip
    -0.06
     엘
    -0.06
     Sick
    -0.06
    abble
    -0.06
     calculating
    -0.06
     powdered
    -0.05
    感到
    -0.05
    POSITIVE LOGITS
    175
    0.07
    "]/
    0.07
    =tf
    0.07
    ความ
    0.07
    569
    0.07
     undergoing
    0.07
    лина
    0.07
    ]}↵
    0.07
    ='',↵
    0.06
    380
    0.06
    Activations Density 0.032%

    No Known Activations