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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 93985
    Prev
    Next
    INDEX
    Explanations

    questions

    np_max-act · gemini-2.0-flash

    It detects tokens that mark dialogue turns—especially question words and first‑person utterances (speaker/question markers) in conversational 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
    exact
    -0.07
     ]↵↵↵
    -0.07
     Kevin
    -0.06
    .Keyword
    -0.06
    ']
    ↵
    ↵
    -0.06
    ]↵↵↵↵
    -0.06
    -fold
    -0.06
    ↵    ↵↵
    -0.06
    ])↵↵
    -0.06
    POSITIVE LOGITS
     marriages
    0.07
     Aim
    0.07
     λειτουργ
    0.07
    лы
    0.07
     ασ
    0.06
     comunidad
    0.06
    (guess
    0.06
    ерами
    0.06
     щодо
    0.06
    ��
    0.06
    Activations Density 0.113%

    No Known Activations