© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 25320
    Prev
    Next
    INDEX
    Explanations

    _fmt

    np_max-act · gemini-2.0-flash

    technical terms related to programming and device drivers.

    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
     curse
    -0.07
     celery
    -0.06
     그러나
    -0.06
    _deploy
    -0.06
    araoh
    -0.06
    IZ
    -0.06
     senin
    -0.06
     można
    -0.06
    _strings
    -0.06
     червня
    -0.06
    POSITIVE LOGITS
    唱
    0.07
    rgb
    0.07
    ubs
    0.06
    _Component
    0.06
    Ports
    0.06
    collectionView
    0.06
     압
    0.06
     موب
    0.06
     الميلاد
    0.06
     ابن
    0.06
    Activations Density 0.002%

    No Known Activations