© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 13104
    Prev
    Next
    INDEX
    Explanations

    comparisons to the past

    np_max-act · gemini-2.0-flash

    The neuron fires on words and phrases that mark past time periods or historical moments (e.g. “back then,” decade/years references, “once,” etc.).

    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
    perfect
    -0.08
     jon
    -0.06
    θρω
    -0.06
     ポ
    -0.06
    pants
    -0.06
    ि�
    -0.06
     Nile
    -0.06
    hevik
    -0.06
    们
    -0.06
    src
    -0.06
    POSITIVE LOGITS
    /D
    0.07
     jumps
    0.06
     código
    0.06
    /autoload
    0.06
    >s
    0.06
    ('-',
    0.06
    /services
    0.06
     Criminal
    0.06
    /entity
    0.06
    .Edit
    0.06
    Activations Density 0.063%

    No Known Activations