© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 13820
    Prev
    Next
    INDEX
    Explanations

    code examples

    np_max-act · gemini-2.0-flash

    The neuron specializes in picking out demonstrative pronouns (e.g. “this,” “these,” “those,” “este/esta/estes”).

    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
    HEL
    -0.06
    。しかし
    -0.06
     ul
    -0.06
     gun
    -0.06
     birbir
    -0.06
     Rio
    -0.06
     metal
    -0.06
    175
    -0.06
    strpos
    -0.06
    _DOMAIN
    -0.06
    POSITIVE LOGITS
    εχ
    0.06
     hed
    0.06
     connected
    0.06
     FINSEQ
    0.06
    aturated
    0.06
    -context
    0.06
    abh
    0.06
    .CV
    0.06
     bezier
    0.06
    nivel
    0.06
    Activations Density 0.075%

    No Known Activations