© 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. 56953
    Prev
    Next
    INDEX
    Explanations

    virtual

    np_max-act · gemini-2.0-flash

    The neuron fires on tokens that mark the VTuber persona—things like “vtuber,” the character’s NAME_ID tags, Live2D references, and other identity-label bits.

    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
     pca
    -0.06
     birlikte
    -0.06
    nea
    -0.06
    _ap
    -0.06
    ECTOR
    -0.06
    american
    -0.06
    エル
    -0.06
    _stdout
    -0.06
    urse
    -0.06
    محمد
    -0.06
    POSITIVE LOGITS
     kommun
    0.07
    (月
    0.07
    -token
    0.07
     Carson
    0.06
     먹
    0.06
    rels
    0.06
    (Token
    0.06
     Opposition
    0.06
    theon
    0.06
    (lock
    0.06
    Activations Density 0.006%

    No Known Activations