© 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 EvalsExportsAPI 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. 15-RESID-POST-AA
    11. 125942
    Prev
    Next
    INDEX
    Explanations

    The

    np_max-act · gemini-2.0-flash

    tokens that begin news-article leads or datelines (particularly the sentence-initial "The" used at the start of news paragraphs).

    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
    ेकर
    -0.06
    摇
    -0.06
     إلا
    -0.06
    avou
    -0.06
    备份
    -0.06
    など
    -0.06
     sông
    -0.06
     thereof
    -0.06
    _font
    -0.06
     airy
    -0.06
    POSITIVE LOGITS
    Ali
    0.07
    ...");↵
    0.07
     Clin
    0.07
    Kin
    0.06
    pite
    0.06
    、↵↵
    0.06
    Mrs
    0.06
    Public
    0.06
    Professional
    0.06
     align
    0.06
    Activations Density 0.033%

    No Known Activations