© 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. 105868
    Prev
    Next
    INDEX
    Explanations

    statements and assurances

    np_max-act · gemini-2.0-flash

    language indicating assurances or promises—reported statements asserting that something is or will be true or guaranteed.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
     Cha
    -0.06
    aft
    -0.06
    ум
    -0.06
    rá
    -0.06
    哲
    -0.06
     Рас
    -0.06
    oğ
    -0.06
    ele
    -0.06
    ehicle
    -0.06
    Beer
    -0.06
    POSITIVE LOGITS
    _FLAGS
    0.07
    *s
    0.07
     ServiceException
    0.07
    _SETTING
    0.07
    nEnter
    0.07
     saturated
    0.07
    ัฐบาล
    0.07
    .Resource
    0.07
     FormBuilder
    0.07
     nuances
    0.06
    Activations Density 0.053%

    No Known Activations