© 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 EvalsExportsinterp-engineNEWAPI 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. 58084
    Prev
    Next
    INDEX
    Explanations

    dependent

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of statistical “dependent” (and to a lesser extent “independent”) variables.

    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
     tour
    -0.07
     tor
    -0.06
     тепер
    -0.06
    스터
    -0.06
    aml
    -0.06
     기억
    -0.06
     Diamonds
    -0.06
     SME
    -0.06
    Ctl
    -0.06
     uniq
    -0.06
    POSITIVE LOGITS
    ってる
    0.06
     GOODS
    0.06
    agen
    0.06
    ROWN
    0.06
    rem
    0.06
    retorno
    0.06
    æ
    0.06
     FUNCTIONS
    0.06
     There
    0.06
    ified
    0.06
    Activations Density 0.009%

    No Known Activations