© 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. 29565
    Prev
    Next
    INDEX
    Explanations

    public transportation

    np_max-act · gemini-2.0-flash

    phrases expressing customer satisfaction and public transportation themes.

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

    The neuron detects mentions of bus transit schedules and next‐arrival information.

    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
    -worker
    -0.07
     DA
    -0.06
    .chain
    -0.06
    ूट
    -0.06
    _rule
    -0.06
    GEN
    -0.06
    Bits
    -0.06
    .connections
    -0.06
    (ref
    -0.06
    /cmd
    -0.06
    POSITIVE LOGITS
     smlou
    0.07
    .JButton
    0.07
    чивается
    0.07
     Při
    0.07
     нату
    0.07
    ΜΑ
    0.06
     zku
    0.06
    ickerView
    0.06
     borderSide
    0.06
    _typeof
    0.06
    Activations Density 0.017%

    No Known Activations