© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 89688
    Prev
    Next
    INDEX
    Explanations

    calculate

    np_max-act · gemini-2.0-flash

    The neuron is detecting numeric tokens used in dates or timestamps (e.g. day/month/year and time elements).

    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
     superficial
    -0.07
     textual
    -0.07
     dosy
    -0.07
     workstation
    -0.06
    €€
    -0.06
     crossover
    -0.06
     matlab
    -0.06
    IDENT
    -0.06
     helps
    -0.06
    rint
    -0.06
    POSITIVE LOGITS
     đá
    0.07
    avs
    0.07
     منابع
    0.06
    บาง
    0.06
    اریخ
    0.06
     chua
    0.06
    svp
    0.06
     Να
    0.06
     Send
    0.06
    (milliseconds
    0.06
    Activations Density 0.178%

    No Known Activations