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. 22480
    Prev
    Next
    INDEX
    Explanations

    built-in features

    np_max-act · gemini-2.0-flash

    products related to advanced networking solutions that integrate dual-band Wi-Fi capabilities.

    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
     graduation
    -0.07
    ají
    -0.07
     svým
    -0.07
     jméno
    -0.07
     глуб
    -0.06
    ्रदर
    -0.06
     dann
    -0.06
     initiator
    -0.06
     écrit
    -0.06
     Cleanup
    -0.06
    POSITIVE LOGITS
    Program
    0.06
    _URI
    0.06
     Renault
    0.06
     Workspace
    0.06
    game
    0.06
    �
    0.06
    _generated
    0.06
    /copyleft
    0.06
     origins
    0.06
    .workspace
    0.06
    Activations Density 0.013%

    No Known Activations