© 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
    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. 44700
    Prev
    Next
    INDEX
    Explanations

    Comments

    np_max-act · gemini-2.0-flash

    The neuron detects the “Comments” header (and related markers) that denote the start of a comment section.

    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
     Support
    -0.07
     scholarship
    -0.07
     survival
    -0.07
     Ax
    -0.06
     Past
    -0.06
    ición
    -0.06
     profiling
    -0.06
     sha
    -0.06
     scholar
    -0.06
    스템
    -0.06
    POSITIVE LOGITS
     중요한
    0.07
     확실
    0.07
    -prepend
    0.07
     проблема
    0.06
    options
    0.06
     대한민국
    0.06
     voc
    0.06
    ,Th
    0.06
    하다
    0.06
     reasoned
    0.06
    Activations Density 0.002%

    No Known Activations