© 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. 9502
    Prev
    Next
    INDEX
    Explanations

    let

    np_max-act · gemini-2.0-flash

    explicit, pornographic or vulgar language, especially tied to aggressive, violent, or taboo sexual themes and body-related fetishes

    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
    ř
    -0.07
     prev
    -0.07
     iy
    -0.07
     Liverpool
    -0.07
     IK
    -0.06
    Tk
    -0.06
     chiff
    -0.06
    dehyde
    -0.06
     Warren
    -0.06
     XV
    -0.06
    POSITIVE LOGITS
     writeTo
    0.07
     оскільки
    0.06
    ,他们
    0.06
     району
    0.06
     divorced
    0.05
    RowAt
    0.05
     inherits
    0.05
     stayed
    0.05
     kutje
    0.05
    <IActionResult
    0.05
    Activations Density 1.569%

    No Known Activations