© 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. 92269
    Prev
    Next
    INDEX
    Explanations

    IMG

    np_max-act · gemini-2.0-flash

    The neuron activates on anonymized placeholder tokens (e.g. NAME_##) used to stand in for actual entity names.

    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
    Some
    -0.07
     Laboratories
    -0.07
     drainage
    -0.06
     ciclo
    -0.06
    bris
    -0.06
     Framework
    -0.06
    culture
    -0.06
    난
    -0.06
    _nb
    -0.06
    nor
    -0.06
    POSITIVE LOGITS
    .
↵
    0.07
    sha
    0.07
    ignment
    0.07
     생성
    0.06
    ेड
    0.06
    ablish
    0.06
    /ch
    0.06
    /from
    0.06
     trữ
    0.06
    ={"/
    0.06
    Activations Density 0.085%

    No Known Activations