© 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. 42968
    Prev
    Next
    INDEX
    Explanations

    version released

    np_max-act · gemini-2.0-flash

    The neuron detects the special sequence tokens used to mark and separate conversation headers and end‐of‐turn markers (e.g. `<|start_header_id|>`, `<|eot_id|>`).

    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
     SERVICE
    -0.06
     아닌
    -0.06
    	glBind
    -0.06
    нев
    -0.06
    .setProgress
    -0.06
    dispatcher
    -0.06
    ीप
    -0.06
    emale
    -0.06
     تق
    -0.05
    (channel
    -0.05
    POSITIVE LOGITS
    .keyCode
    0.07
     \''
    0.07
    SN
    0.07
    heet
    0.07
     redistrib
    0.07
    ταση
    0.07
     Başkanı
    0.07
     �
    0.06
    -、
    0.06
    ��
    0.06
    Activations Density 0.021%

    No Known Activations