© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 56580
    Prev
    Next
    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash

    This neuron detects code patterns for merging or joining datasets (e.g., the “merge” call with “by” and “how”/“.x”/“.y” parameters).

    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
     цвета
    -0.06
     sit
    -0.06
     interview
    -0.06
    pur
    -0.06
    .face
    -0.06
     było
    -0.06
    梅
    -0.06
    tip
    -0.06
    _SUPPLY
    -0.06
     precip
    -0.06
    POSITIVE LOGITS
     objectively
    0.07
     draws
    0.06
    etic
    0.06
     subur
    0.06
    ilm
    0.06
    USA
    0.06
     Dahl
    0.06
    	ft
    0.06
    alsa
    0.06
    ="--
    0.06
    Activations Density 0.007%

    No Known Activations