© 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. 4339
    Prev
    Next
    INDEX
    Explanations

    be

    np_max-act · gemini-2.0-flash

    Instances of legal-style prohibitions or negations (phrases expressing that something must not or may not be done), especially in license/notice 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
    ////////////////////////////////////////////////////////
    -0.07
     يو
    -0.06
    訊
    -0.06
     ста
    -0.06
    incy
    -0.06
    ctrl
    -0.06
    再
    -0.06
    mach
    -0.06
     ян
    -0.06
     Presbyterian
    -0.06
    POSITIVE LOGITS
     elasticity
    0.06
    부
    0.06
     speeds
    0.06
    убли
    0.06
    _Test
    0.06
     Tester
    0.06
     millones
    0.06
     Essex
    0.06
    _FACE
    0.06
    delimiter
    0.06
    Activations Density 0.001%

    No Known Activations