© 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. 124952
    Prev
    Next
    INDEX
    Explanations

    Metro lines

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect mentions of metro (subway) line identifiers (e.g. “Line 5,” “/blue line,” station connections) in transport descriptions.

    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
     occur
    -0.08
    et
    -0.07
     genetics
    -0.07
    LERİ
    -0.06
     Garner
    -0.06
     bounds
    -0.06
    気が
    -0.06
    VertexUvs
    -0.06
     Genetics
    -0.06
     personals
    -0.06
    POSITIVE LOGITS
    /update
    0.07
    _pieces
    0.07
    ulse
    0.06
    velop
    0.06
    óng
    0.06
    ingle
    0.06
    Rename
    0.06
    REAK
    0.06
    izabeth
    0.06
    toggle
    0.06
    Activations Density 0.004%

    No Known Activations