© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 105823
    Prev
    Next
    INDEX
    Explanations

    exiting

    np_max-act · gemini-2.0-flash

    Python code that utilizes threading to run a function with arguments.

    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
     beneficiation
    -0.08
     додатков
    -0.07
     senate
    -0.06
     vyž
    -0.06
    yl
    -0.06
     soil
    -0.06
    ований
    -0.06
    *>::
    -0.06
     پیشنه
    -0.06
    (Self
    -0.06
    POSITIVE LOGITS
     τι
    0.06
    /logo
    0.06
    ertia
    0.06
     crashing
    0.06
    met
    0.06
     dve
    0.06
    ='.
    0.06
    exist
    0.06
    ]<
    0.06
     putas
    0.06
    Activations Density 0.013%

    No Known Activations