© 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. 11-RESID-POST-AA
    11. 104732
    Prev
    Next
    INDEX
    Explanations

    Scientific explanations

    np_max-act · gemini-2.0-flash

    scientific terminology and concepts related to stellar and astrophysical phenomena.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ｲ
    -0.06
    يان
    -0.06
     sotto
    -0.06
     Perf
    -0.06
     ایرانی
    -0.06
    .Initialize
    -0.06
    rut
    -0.06
    覺
    -0.06
     Clair
    -0.06
    ề
    -0.05
    POSITIVE LOGITS
    香港
    0.07
     sealed
    0.06
     κατά
    0.06
     نیم
    0.06
    řeh
    0.06
    ंध
    0.06
    ogie
    0.06
    clipse
    0.06
    ||
    0.06
     syn
    0.06
    Activations Density 0.044%

    No Known Activations