© 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
    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. 1706
    Prev
    Next
    INDEX
    Explanations

    LessWrong content

    np_max-act · gemini-2.0-flash

    mentions of AI/AI‑safety, longtermism, and related rationalist community topics (e.g., LessWrong, MIRI, Singularity).

    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
     ethical
    -0.08
     khóa
    -0.06
    (Layout
    -0.06
     expectancy
    -0.06
    _platform
    -0.06
     WHETHER
    -0.06
     originated
    -0.06
     rows
    -0.06
    (secret
    -0.06
    ıyoruz
    -0.06
    POSITIVE LOGITS
    bedo
    0.07
    ONS
    0.07
    protocols
    0.06
    agment
    0.06
    .AppSettings
    0.06
    ederland
    0.06
     implicated
    0.06
    ...)
    0.06
    _rank
    0.06
     Manila
    0.06
    Activations Density 0.237%

    No Known Activations