© 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. 27996
    Prev
    Next
    INDEX
    Explanations

    ensure/sure

    np_max-act · gemini-2.0-flash

    The neuron fires on words expressing assurances or obligations—particularly on “ensure” and the phrase “make sure.”

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

    prominent chemical companies and their contributions to the industry.

    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
     Manager
    -0.07
    allocator
    -0.07
     Romanian
    -0.07
    ADOS
    -0.07
     Marketplace
    -0.07
     شده
    -0.06
     manager
    -0.06
    Threshold
    -0.06
     CancellationToken
    -0.06
    _children
    -0.06
    POSITIVE LOGITS
     предус
    0.08
    panic
    0.07
     contribute
    0.07
     puls
    0.07
    .esp
    0.06
     $_
    0.06
     úřad
    0.06
    _skills
    0.06
     tons
    0.06
     проек
    0.06
    Activations Density 0.030%

    No Known Activations