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. 80910
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    the main thing this neuron does is find references to file‐archiving and backup operations (creating, extracting, deleting, or restoring archives) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    code snippets related to file manipulation in cloud services.

    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
    -end
    -0.07
    il
    -0.07
     масло
    -0.07
     thế
    -0.06
     criminal
    -0.06
    ежду
    -0.06
     خارجی
    -0.06
    .webdriver
    -0.06
    -memory
    -0.06
     tourist
    -0.06
    POSITIVE LOGITS
     ओ
    0.07
     評
    0.06
    ]=(
    0.06
    PW
    0.06
    .EventArgs
    0.06
    ombie
    0.06
     �
    0.06
     actualizar
    0.06
    ]-
    0.06
    .tools
    0.06
    Activations Density 0.265%

    No Known Activations