© 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. 12513
    Prev
    Next
    INDEX
    Explanations

    months/seasons

    np_max-act · gemini-2.0-flash

    This neuron activates on date references (e.g. month names and associated date numbers).

    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
     surveyed
    -0.06
     HO
    -0.06
    image
    -0.06
     vessel
    -0.06
     Mad
    -0.06
     grabs
    -0.06
     voice
    -0.06
     village
    -0.06
    _repository
    -0.06
     cameras
    -0.06
    POSITIVE LOGITS
    ]&
    0.07
     этим
    0.07
    优
    0.07
     Pillow
    0.07
    rně
    0.06
     zpracování
    0.06
    قى
    0.06
    AndPassword
    0.06
     большин
    0.06
    imenti
    0.06
    Activations Density 0.011%

    No Known Activations