© 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. 47956
    Prev
    Next
    INDEX
    Explanations

    minutes

    np_max-act · gemini-2.0-flash

    The neuron detects relative‐time expressions, especially numeric day offsets and their connectors (e.g. “n days before/after” reference points).

    oai_token-act-pair · o4-mini
    Triggered by @xinyanhu8

    phrases related to age comparisons and calculations.

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    ild
    -0.06
    ौद
    -0.06
    .(
    -0.06
    zept
    -0.06
    ’є
    -0.06
    Ipv
    -0.06
     Funktion
    -0.06
    Markdown
    -0.06
    _hr
    -0.06
     дод
    -0.06
    POSITIVE LOGITS
    conut
    0.07
    DATA
    0.07
     onPause
    0.07
     inspires
    0.07
    pla
    0.07
     Lester
    0.07
    kb
    0.07
     producer
    0.07
    likelihood
    0.07
     LANG
    0.06
    Activations Density 0.008%

    No Known Activations