© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 50054
    Prev
    Next
    INDEX
    Explanations

    ews

    np_max-act · gemini-2.0-flash

    high-register, formal or technical vocabulary—rare, Latinate terms and precise analytical phrasing typically used in academic or journalistic prose.

    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
    okay
    -0.07
     progressed
    -0.07
    laughter
    -0.07
     Uno
    -0.07
     seal
    -0.07
     Birds
    -0.07
    …but
    -0.06
    …it
    -0.06
    �
    -0.06
     laughing
    -0.06
    POSITIVE LOGITS
     Yorkers
    0.06
     chẳng
    0.06
     especial
    0.06
    wechat
    0.06
    /entities
    0.06
    _DENIED
    0.06
    ostringstream
    0.06
     increasingly
    0.06
     exhilar
    0.06
     underestimate
    0.06
    Activations Density 6.225%

    No Known Activations