© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 74824
    Prev
    Next
    INDEX
    Explanations

    code or data

    np_max-act · gemini-2.0-flash

    technical terms and vector attributes related to computer graphics and programming.

    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
    ermann
    -0.07
    ERS
    -0.06
    mamız
    -0.06
    贵
    -0.06
    amas
    -0.06
    Shadow
    -0.06
     Burlington
    -0.06
    νω
    -0.06
    NAS
    -0.06
    UNUSED
    -0.06
    POSITIVE LOGITS
     трех
    0.06
    .Article
    0.06
    ğini
    0.06
    acje
    0.06
    =text
    0.06
    -lived
    0.06
    ảm
    0.06
     หาก
    0.06
     حالة
    0.06
     aure
    0.06
    Activations Density 0.014%

    No Known Activations