© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 58356
    Prev
    Next
    INDEX
    Explanations

    timezone offset

    np_max-act · gemini-2.0-flash

    This neuron responds to the numeric timezone-offset field (e.g. the “020” in “+020”) in document metadata.

    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
     value
    -0.06
    idue
    -0.06
     Value
    -0.06
    ,sum
    -0.06
    .border
    -0.06
     différent
    -0.06
    _NOTICE
    -0.06
    龍
    -0.06
     multinational
    -0.06
    Pair
    -0.06
    POSITIVE LOGITS
     تسم
    0.08
     živ
    0.06
     Whole
    0.06
     []).
    0.06
    课程
    0.06
    치는
    0.06
    optimize
    0.06
    삼
    0.06
    iov
    0.06
    ]</
    0.06
    Activations Density 0.002%

    No Known Activations