© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 59088
    Prev
    Next
    INDEX
    Explanations

    epoch

    np_max-act · gemini-2.0-flash

    The neuron specifically looks for numeric “year” tokens (dates like 2023, 2024) in headers or metadata.

    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
     киш
    -0.07
    -management
    -0.06
    ฒ
    -0.06
    �
    -0.06
     efforts
    -0.06
     onemoc
    -0.06
    undle
    -0.06
    ､
    -0.06
     AccessToken
    -0.06
     Jed
    -0.06
    POSITIVE LOGITS
    xdf
    0.07
    .Tipo
    0.06
    _GEN
    0.06
     pré
    0.06
    .General
    0.06
    <Base
    0.06
    <src
    0.06
     cyber
    0.06
    /lab
    0.06
    _EQ
    0.05
    Activations Density 0.010%

    No Known Activations