© 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. 74103
    Prev
    Next
    INDEX
    Explanations

    anonymous

    np_max-act · gemini-2.0-flash

    The neuron fires on occurrences of the word “anonymous” (as in anonymous access or anonymous users).

    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
     таблиц
    -0.07
    eds
    -0.06
     spices
    -0.06
     lun
    -0.06
     Parks
    -0.06
    species
    -0.06
    ascar
    -0.06
    LAS
    -0.06
     Stadium
    -0.06
     Mercy
    -0.06
    POSITIVE LOGITS
    ทะ
    0.06
    视
    0.06
     accessToken
    0.06
    .assets
    0.06
     weil
    0.06
    oracle
    0.06
    ’acc
    0.06
    _com
    0.06
     히
    0.06
    ")))
    0.06
    Activations Density 0.002%

    No Known Activations