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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 118266
    Prev
    Next
    INDEX
    Explanations

    non-English

    np_max-act · gemini-2.0-flash

    expressions of personal experience or emotion related to a place or culture.

    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
    261
    -0.07
     Logic
    -0.07
     twenty
    -0.06
    ucky
    -0.06
    admin
    -0.06
     stories
    -0.06
     blood
    -0.06
     trig
    -0.06
     mirrors
    -0.06
    public
    -0.06
    POSITIVE LOGITS
     wykon
    0.07
     sắc
    0.07
     irradi
    0.07
     взя
    0.07
     измер
    0.07
     fortified
    0.06
     decipher
    0.06
    ポート
    0.06
     пунк
    0.06
     incarn
    0.06
    Activations Density 0.406%

    No Known Activations