© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 57890
    Prev
    Next
    INDEX
    Explanations

    email confidentiality disclaimer

    np_max-act · gemini-2.0-flash

    The neuron predominantly activates on terms used in email or document confidentiality and legal‐privilege disclaimers (e.g. “confidential,” “privileged,” “intended,” “recipient,” “disclosure,” etc.).

    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
     صورت
    -0.06
    Credential
    -0.06
    .logging
    -0.06
    OS
    -0.06
     Quint
    -0.06
     granddaughter
    -0.06
     organizational
    -0.06
     Speakers
    -0.06
    048
    -0.06
    (IS
    -0.06
    POSITIVE LOGITS
    >(↵
    0.07
    ，都
    0.07
    '>$
    0.06
    ＞
    0.06
     GX
    0.06
     теор
    0.06
    بيع
    0.06
    stash
    0.06
    čast
    0.06
     mashed
    0.06
    Activations Density 0.006%

    No Known Activations