© 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. 74634
    Prev
    Next
    INDEX
    Explanations

    Articles or Time

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of specific time‐period expressions (e.g. “during a specific period of time,” “one year,” “period,” “time”).

    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
    .textView
    -0.08
    ATAR
    -0.07
     ít
    -0.06
    ा�
    -0.06
     木
    -0.06
    Ty
    -0.06
    Aw
    -0.06
    ToF
    -0.06
     जव
    -0.06
    านคร
    -0.06
    POSITIVE LOGITS
     infos
    0.07
    prov
    0.06
     tracked
    0.06
     lifestyle
    0.06
     ;;=
    0.06
     moderated
    0.06
    cdr
    0.06
    Scope
    0.06
     abandoning
    0.06
    -url
    0.06
    Activations Density 0.034%

    No Known Activations