© 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. 89619
    Prev
    Next
    INDEX
    Explanations

    scientific/technical descriptions

    np_max-act · gemini-2.0-flash

    This neuron fires on parameter names or technical identifiers in code or method descriptions—most strongly on “haystack” and “needle” in the custom strstr example.

    oai_token-act-pair · o4-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
     mild
    -0.06
     refuge
    -0.06
    .Device
    -0.06
     flourishing
    -0.06
    ELY
    -0.06
     insight
    -0.06
    _capacity
    -0.06
     disple
    -0.06
    _caption
    -0.06
     Camb
    -0.06
    POSITIVE LOGITS
    !';↵
    0.07
    نجليزية
    0.07
    ={↵
    0.07
     UserID
    0.06
     resurrection
    0.06
    età
    0.06
    Wizard
    0.06
    ///
↵
    0.06
    Upload
    0.06
     vẫn
    0.06
    Activations Density 0.518%

    No Known Activations