© 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. 8925
    Prev
    Next
    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash

    This neuron detects table-structure delimiters, specifically the pipe characters (“|”) used to separate columns in tabular data.

    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
    _th
    -0.07
    esterday
    -0.07
     onSelect
    -0.06
    .Hour
    -0.06
     toJSON
    -0.06
     heroine
    -0.06
     teenager
    -0.06
     Samsung
    -0.06
    第四
    -0.06
     stru
    -0.06
    POSITIVE LOGITS
    кам
    0.07
    \data
    0.07
    달
    0.07
     servidor
    0.06
    '][
    0.06
    =[],
    0.06
    .todos
    0.06
    >{$
    0.06
    .rstrip
    0.06
    paces
    0.06
    Activations Density 0.016%

    No Known Activations