© 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. 11-RESID-POST-AA
    11. 45261
    Prev
    Next
    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash

    code snippets and programming-related keywords in the context of software development.

    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
    resolution
    -0.07
     evaluating
    -0.07
    ＋
    -0.06
    -than
    -0.06
    _Pin
    -0.06
    usic
    -0.06
     coin
    -0.06
     Society
    -0.06
    armacy
    -0.06
    ,C
    -0.06
    POSITIVE LOGITS
    ulares
    0.07
     sitios
    0.07
     Hearing
    0.06
    Bill
    0.06
    έ
    0.06
    ]').
    0.06
    ики
    0.06
    .lineTo
    0.06
    -made
    0.06
     spheres
    0.06
    Activations Density 0.023%

    No Known Activations