© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 91575
    Prev
    Next
    INDEX
    Explanations

    describing event times

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on clock-time expressions (e.g. “6:00 pm,” “7:30 am,” “starts at”) in event or schedule 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
     Hass
    -0.08
     tung
    -0.08
    ARGE
    -0.06
    YRO
    -0.06
    _username
    -0.06
    Password
    -0.06
     solutions
    -0.06
    udge
    -0.06
    arge
    -0.06
    ,path
    -0.06
    POSITIVE LOGITS
    @SuppressWarnings
    0.07
    _tele
    0.07
    ……
    0.07
     giy
    0.06
     Advertisement
    0.06
     GridView
    0.06
    .DateTimeField
    0.06
    ToolStripMenuItem
    0.06
     killings
    0.06
    RoutingModule
    0.06
    Activations Density 0.018%

    No Known Activations