© 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. 47892
    Prev
    Next
    INDEX
    Explanations

    separation

    np_max-act · gemini-2.0-flash

    The neuron consistently detects the word “separation” (and its morphological variants) in technical descriptions.

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

    processes related to separation and purification techniques in chemical production.

    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
     Vide
    -0.07
    OfClass
    -0.07
    .magic
    -0.07
     coding
    -0.07
    ________
    -0.07
    imple
    -0.06
    <Cell
    -0.06
     passes
    -0.06
     Poly
    -0.06
    Large
    -0.06
    POSITIVE LOGITS
     undecided
    0.07
     slipping
    0.07
     bourbon
    0.06
     آی
    0.06
    领
    0.06
    üp
    0.06
    ическая
    0.06
    ensis
    0.06
     ft
    0.06
    _local
    0.06
    Activations Density 0.003%

    No Known Activations