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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 7629
    Prev
    Next
    INDEX
    Explanations

    video games

    np_max-act · gemini-2.0-flash

    sentences or phrases giving video-game build/guide advice (items, builds, level progression and how-to tips).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kansas
    -0.07
    azı
    -0.07
    _inputs
    -0.07
    женер
    -0.07
    LoginForm
    -0.07
     Exc
    -0.07
     Egg
    -0.07
    ائه
    -0.07
    ambi
    -0.07
     roof
    -0.07
    POSITIVE LOGITS
    rawtypes
    0.07
    �
    0.07
    unfinished
    0.06
    	glfw
    0.06
     quake
    0.06
    にて
    0.06
     isActive
    0.06
     düzenlenen
    0.05
    彩票
    0.05
    	cf
    0.05
    Activations Density 0.032%

    No Known Activations