Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 21800
    Prev
    Next
    INDEX
    Explanations

    .Duration

    np_max-act · gemini-2.0-flash

    code related to task scheduling and management.

    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
     tracking
    -0.06
    .Score
    -0.06
    .Screen
    -0.06
    (category
    -0.06
    電子
    -0.06
     Scratch
    -0.06
    Identity
    -0.06
     level
    -0.06
     refriger
    -0.06
    도별
    -0.06
    POSITIVE LOGITS
    ',↵↵
    0.07
    στ
    0.07
    mir
    0.07
    .FILL
    0.07
     demol
    0.06
     XPAR
    0.06
     omission
    0.06
    "]:
    0.06
     khởi
    0.06
    ulfilled
    0.06
    Activations Density 0.001%

    No Known Activations