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. 73111
    Prev
    Next
    INDEX
    Explanations

    labels

    np_max-act · gemini-2.0-flash

    YAML structures pertaining to Kubernetes resource definitions.

    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
    prech
    -0.07
    ddit
    -0.06
     شخصی
    -0.06
     Bearings
    -0.06
     Zombies
    -0.06
     یافت
    -0.06
    PTH
    -0.06
     HIS
    -0.06
    ตรวจ
    -0.06
    ONGODB
    -0.06
    POSITIVE LOGITS
     corpor
    0.08
    lotte
    0.07
    utable
    0.07
    tweet
    0.07
     nbytes
    0.06
    ikel
    0.06
    ufact
    0.06
     Classifier
    0.06
     bitcoin
    0.06
     respons
    0.06
    Activations Density 0.001%

    No Known Activations