© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 126568
    Prev
    Next
    INDEX
    Explanations

    -d

    np_max-act · gemini-2.0-flash

    The neuron fires on the special header‐delimiter tokens (e.g. the “<|start_header_id|>” and “<|end_header_id|>” markers), i.e. it detects the metadata header tags.

    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
    ahtar
    -0.07
     realpath
    -0.07
     вероят
    -0.07
     genitals
    -0.06
     Peripheral
    -0.06
    كال
    -0.06
    šak
    -0.06
    (element
    -0.06
    thritis
    -0.06
    406
    -0.06
    POSITIVE LOGITS
     arbitration
    0.07
     dwind
    0.07
     arp
    0.07
    Presentation
    0.07
    .Compiler
    0.07
     semiclass
    0.06
    页面存档备份
    0.06
    "data
    0.06
     Information
    0.06
     distress
    0.06
    Activations Density 0.124%

    No Known Activations