© 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. 59364
    Prev
    Next
    INDEX
    Explanations

    some

    np_max-act · gemini-2.0-flash

    The neuron activates on connective and relational function words (e.g. “with,” “which,” “has,” “is,” “the,” “and”) that introduce or link attributes in object‐description instructions.

    oai_token-act-pair · o4-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
     pulls
    -0.06
     conduc
    -0.06
     coc
    -0.06
     списка
    -0.06
     iniciar
    -0.06
    /people
    -0.06
     advance
    -0.06
    Leaders
    -0.06
    .St
    -0.06
     focuses
    -0.06
    POSITIVE LOGITS
    atically
    0.06
     روح
    0.06
     첨부파일
    0.06
    angler
    0.06
    okane
    0.06
     Cornell
    0.06
    uner
    0.06
     liable
    0.06
    ffmpeg
    0.06
     callback
    0.06
    Activations Density 0.003%

    No Known Activations