© 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
    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. 71939
    Prev
    Next
    INDEX
    Explanations

    Dear letters

    np_max-act · gemini-2.0-flash

    Tokens that name or address the recipient of a formal/business message (salutations/addressee titles).

    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
    ]});↵
    -0.07
    _Static
    -0.07
    =headers
    -0.06
     comforts
    -0.06
    _approx
    -0.06
     Phaser
    -0.06
    ومتر
    -0.06
     latino
    -0.06
    ')])↵
    -0.06
    POSITIVE LOGITS
    Es
    0.06
     ред
    0.06
    inging
    0.06
    473
    0.06
     flatt
    0.06
     ведь
    0.06
    666
    0.06
    ΟΛ
    0.06
     خاصة
    0.06
     dell
    0.06
    Activations Density 0.024%

    No Known Activations