© 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. 124236
    Prev
    Next
    INDEX
    Explanations

    forward

    np_max-act · gemini-2.0-flash

    the basic structural components and processes involved in implementing various neural networks in PyTorch.

    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
     situación
    -0.07
    标
    -0.07
     discrimin
    -0.06
     다른
    -0.06
     ribs
    -0.06
     heute
    -0.06
    \Repositories
    -0.06
     �
    -0.06
     nella
    -0.06
     illust
    -0.06
    POSITIVE LOGITS
     앉
    0.07
    nictvím
    0.06
     cpt
    0.06
    ≦
    0.06
     prů
    0.06
    .Ed
    0.06
    ARED
    0.06
    OTTOM
    0.06
    167
    0.06
    alc
    0.06
    Activations Density 0.004%

    No Known Activations