© 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. 59067
    Prev
    Next
    INDEX
    Explanations

    stopwords

    np_max-act · gemini-2.0-flash

    This neuron responds to mentions of text‐preprocessing operations (e.g. tokenization, stop-word removal, stemming/lemmatization).

    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
    TypeDef
    -0.07
     Whether
    -0.06
    vil
    -0.06
     licenses
    -0.06
    sı
    -0.06
     iki
    -0.06
    vy
    -0.06
    logan
    -0.06
     võ
    -0.06
     naší
    -0.06
    POSITIVE LOGITS
     Frem
    0.07
    ература
    0.07
     downtime
    0.06
    ostat
    0.06
    _point
    0.06
    休
    0.06
     �
    0.06
     interruption
    0.06
     stopwords
    0.06
    criminal
    0.06
    Activations Density 0.002%

    No Known Activations