© 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. 40936
    Prev
    Next
    INDEX
    Explanations

    distance

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of physical distances or measurements (e.g., numeric values with units or location-relative distance phrases).

    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
    _singular
    -0.06
    осред
    -0.06
    Paid
    -0.06
    .bin
    -0.06
     Singer
    -0.06
     specialize
    -0.06
    [selected
    -0.06
    Viol
    -0.06
    ine
    -0.06
    ]=="
    -0.06
    POSITIVE LOGITS
     kommun
    0.07
     geographical
    0.07
    _CONSTANT
    0.06
    .getDeclared
    0.06
     крем
    0.06
     Ukraj
    0.06
     function
    0.06
     اون
    0.06
     characterization
    0.06
     داستان
    0.06
    Activations Density 0.015%

    No Known Activations