© 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. 124942
    Prev
    Next
    INDEX
    Explanations

    3

    np_max-act · gemini-2.0-flash

    The neuron responds to uppercase abbreviations and initialisms (multi-letter acronyms).

    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
    ்
    -0.07
    ./
    -0.07
     Eisenhower
    -0.07
     ppl
    -0.07
    stdint
    -0.06
    <translation
    -0.06
    ursday
    -0.06
     },↵↵
    -0.06
    ฺ
    -0.06
    jourd
    -0.06
    POSITIVE LOGITS
     representative
    0.06
     Namespace
    0.06
     gravid
    0.06
     cancel
    0.06
     mourn
    0.06
     خواه
    0.06
     अवध
    0.06
     пропози
    0.06
    وير
    0.06
     брос
    0.06
    Activations Density 0.042%

    No Known Activations