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. 104325
    Prev
    Next
    INDEX
    Explanations

    DataSet

    np_max-act · gemini-2.0-flash

    SQL or database-related queries and operations.

    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
    TASK
    -0.07
    _root
    -0.07
    Palindrome
    -0.07
    pygame
    -0.07
     ****************************************
    -0.06
    _classes
    -0.06
     Horton
    -0.06
    ])↵↵
    -0.06
    ­های
    -0.06
    ~~~~~~~~~~~~~~~~
    -0.06
    POSITIVE LOGITS
     DataSet
    0.08
    ะ
    0.07
    ovah
    0.07
    ive
    0.07
    )data
    0.07
    mek
    0.07
     Drake
    0.06
     Brad
    0.06
     financ
    0.06
    καν
    0.06
    Activations Density 0.001%

    No Known Activations