© 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. 15-RESID-POST-AA
    6. 23310
    Prev
    Next
    INDEX
    Explanations

    license

    np_max-act · gemini-2.0-flash

    mentions of software license headers, especially the "MIT License" text.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    �от
    -0.07
    レー
    -0.07
     calf
    -0.06
    ्वप
    -0.06
    'M
    -0.06
    eos
    -0.06
     어
    -0.06
     kiếm
    -0.06
    umm
    -0.06
    linger
    -0.06
    POSITIVE LOGITS
    deployment
    0.07
    _FD
    0.07
    Gran
    0.07
    .redis
    0.06
     condu
    0.06
    .fac
    0.06
    _disk
    0.06
     bağımsız
    0.06
    Conditional
    0.06
     distraction
    0.06
    Activations Density 0.002%

    No Known Activations