© 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. 128498
    Prev
    Next
    INDEX
    Explanations

    The neuron is specialized to detect the model’s internal metadata and control‐sequence tokens (e.g. header markers, start/end identifiers).

    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
     muchos
    -0.07
    ysl
    -0.06
    нение
    -0.06
    _object
    -0.06
    _keys
    -0.06
     cellar
    -0.06
    generation
    -0.06
    Release
    -0.06
    λι
    -0.06
    Raises
    -0.06
    POSITIVE LOGITS
     Пост
    0.07
     (*.
    0.07
     پیشینه
    0.07
     assaulting
    0.06
    MFLOAT
    0.06
     DWC
    0.06
     beet
    0.06
     IDC
    0.06
    .stride
    0.06
     пы
    0.06
    Activations Density 0.047%

    No Known Activations