Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 128227
    Prev
    Next
    INDEX
    Explanations

    information sharing

    np_max-act · gemini-2.0-flash

    mentions of secret or insider tips/hacks—offers of hidden knowledge, tricks, or local-only recommendations about how to do or access things.

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ��
    -0.06
     amor
    -0.06
    出口
    -0.06
    Bluetooth
    -0.06
    omap
    -0.06
    	Expect
    -0.06
     erotico
    -0.06
     品
    -0.06
     nhất
    -0.06
    .AI
    -0.06
    POSITIVE LOGITS
    icion
    0.07
     against
    0.07
    Ub
    0.07
     στις
    0.07
     rot
    0.06
     filesize
    0.06
     MW
    0.06
    licate
    0.06
    servername
    0.06
    abs
    0.06
    Activations Density 0.284%

    No Known Activations