© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 12362
    Prev
    Next
    INDEX
    Explanations

    distance

    np_max-act · gemini-2.0-flash

    programmatic constructs related to distance calculations and spatial data organization.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron detects floating‐point numeric literals (tokens representing decimal numbers).

    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
     สร
    -0.06
    од
    -0.06
    _MA
    -0.06
     �
    -0.06
     �
    -0.06
    zte
    -0.06
    巡
    -0.06
    _tD
    -0.05
     Autof
    -0.05
    erap
    -0.05
    POSITIVE LOGITS
    iggs
    0.08
    �
    0.07
     sensit
    0.07
    ildiği
    0.07
     catast
    0.07
    (coord
    0.07
    Š
    0.07
     pollut
    0.07
     Quảng
    0.06
    ederland
    0.06
    Activations Density 0.020%

    No Known Activations