© 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 EvalsExportsinterp-engineNEWAPI 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. 46779
    Prev
    Next
    INDEX
    Explanations

    if any

    np_max-act · gemini-2.0-flash

    discuss the types and functionalities of language models in artificial intelligence.

    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
    자의
    -0.06
    nonce
    -0.06
    _capacity
    -0.06
    ，存于
    -0.06
     �
    -0.06
     contingency
    -0.06
    ords
    -0.06
    iou
    -0.06
    _available
    -0.06
    culos
    -0.05
    POSITIVE LOGITS
     Heritage
    0.07
     Hil
    0.06
     Eylül
    0.06
     beneficial
    0.06
     sexism
    0.06
     shorthand
    0.06
    ]));↵↵
    0.06
     processo
    0.06
     Vanilla
    0.06
     qt
    0.06
    Activations Density 0.050%

    No Known Activations