© 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. 86123
    Prev
    Next
    INDEX
    Explanations

    safety/risk reassurance

    np_max-act · gemini-2.0-flash

    phrases that signal safety warnings, disclaimers, or content requiring caution (medical, regulatory, or otherwise sensitive).

    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
    Pictures
    -0.07
    "]').
    -0.07
     Taiwanese
    -0.06
    ToLeft
    -0.06
    10
    -0.06
     DN
    -0.06
    Connecting
    -0.06
     strong
    -0.06
     niche
    -0.06
     دانلود
    -0.06
    POSITIVE LOGITS
    prite
    0.07
    ublice
    0.06
    """),↵
    0.06
    undy
    0.06
     �
    0.06
    §
    0.06
    ①
    0.06
    atisf
    0.05
     HuffPost
    0.05
    über
    0.05
    Activations Density 0.307%

    No Known Activations