© 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 (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 110229
    Prev
    Next
    INDEX
    Explanations

    online forums

    np_max-act · gemini-2.0-flash

    This neuron detects when text mentions copying and pasting content from Microsoft Word (i.e. MS Word–origin artifacts).

    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
    packed
    -0.07
    erate
    -0.07
    Union
    -0.07
    Overlay
    -0.07
     abc
    -0.07
     길
    -0.07
     addObject
    -0.07
    aln
    -0.07
    otr
    -0.06
    InitialState
    -0.06
    POSITIVE LOGITS
    ışı
    0.06
    .setVisible
    0.06
     inhabitants
    0.06
    etailed
    0.06
    .,
    0.06
    _DL
    0.06
    featured
    0.06
    IFT
    0.06
     Assistant
    0.06
    ]**
    0.06
    Activations Density 0.295%

    No Known Activations