© 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. 62826
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    instructions or jailbreak attempts that try to override the model's safety/policy constraints and require unrestricted, explicit, or disallowed behavior.

    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
    .defaults
    -0.07
    tras
    -0.07
    tones
    -0.06
     Clyde
    -0.06
    ム
    -0.06
    نز
    -0.06
     NO
    -0.06
     functionName
    -0.06
    DESC
    -0.06
    좌
    -0.06
    POSITIVE LOGITS
    �
    0.07
    اجع
    0.07
     değişik
    0.07
     اندازه
    0.06
    AXB
    0.06
     Bewert
    0.06
    .ask
    0.06
     BufferedWriter
    0.06
     hãy
    0.06
     taille
    0.06
    Activations Density 0.003%

    No Known Activations