© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 50168
    Prev
    Next
    INDEX
    Explanations

    Positive tone

    np_max-act · gemini-2.0-flash

    assertive, high-intensity language that conveys power, capability, dominance, and determined resolve in descriptions or advice.

    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
    rtle
    -0.07
    Adj
    -0.06
     Pence
    -0.06
     jm
    -0.06
     UnityEditor
    -0.06
    �
    -0.06
    .V
    -0.06
    mic
    -0.06
     bore
    -0.06
    (M
    -0.06
    POSITIVE LOGITS
     наб
    0.07
     resides
    0.06
    Grand
    0.06
     yaklaş
    0.06
    -binary
    0.06
    ival
    0.05
     bible
    0.05
     bah
    0.05
     RTWF
    0.05
     cozy
    0.05
    Activations Density 9.381%

    No Known Activations