© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 76263
    Prev
    Next
    INDEX
    Explanations

    net

    np_max-act · gemini-2.0-flash

    code snippets that define convolutional neural network architectures 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
     Param
    -0.07
     Kara
    -0.07
     Slide
    -0.07
     Orchestra
    -0.07
     Welsh
    -0.06
    Slider
    -0.06
     generator
    -0.06
     bulundu
    -0.06
    _font
    -0.06
     Drivers
    -0.06
    POSITIVE LOGITS
    coes
    0.07
    住宅
    0.06
    adol
    0.06
    θεση
    0.06
     ".",
    0.06
     그것
    0.06
    ьют
    0.06
     §§
    0.06
    قي
    0.06
    Jessica
    0.06
    Activations Density 0.005%

    No Known Activations