© 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. 7-RESID-POST-AA
    11. 64714
    Prev
    Next
    INDEX
    Explanations

    of many

    np_max-act · gemini-2.0-flash

    This neuron detects words and phrases indicating large quantities or crowds (e.g., "lot," "many," "people," "a lot of").

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     privateKey
    -0.07
    dfd
    -0.07
     Restr
    -0.06
    .hours
    -0.06
     Keith
    -0.06
    boro
    -0.06
    .initial
    -0.06
     Hours
    -0.06
    Form
    -0.06
    cxx
    -0.06
    POSITIVE LOGITS
     Retrieved
    0.07
     salvar
    0.07
     �
    0.06
     τό
    0.06
    _bullet
    0.06
     numerous
    0.06
    (LOG
    0.06
    (td
    0.06
    ‐
    0.06
     zahl
    0.06
    Activations Density 0.043%

    No Known Activations