Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 100246
    Prev
    Next
    INDEX
    Explanations

    crude

    np_max-act · gemini-2.0-flash

    medical terminology related to diabetes and its associated risks.

    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
     boiled
    -0.07
    UTF
    -0.07
    flation
    -0.07
     articles
    -0.06
    采购
    -0.06
     appended
    -0.06
     ultr
    -0.06
    Flush
    -0.06
    سوب
    -0.06
    われる
    -0.06
    POSITIVE LOGITS
    ?v
    0.07
     Tarih
    0.07
     Relations
    0.06
     Кам
    0.06
     odom
    0.06
     والت
    0.06
    ;j
    0.06
    봉
    0.06
    byname
    0.06
    .npy
    0.06
    Activations Density 0.028%

    No Known Activations