© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 39134
    Prev
    Next
    INDEX
    Explanations

    et

    np_max-act · gemini-2.0-flash

    This neuron activates on occurrences of the substring “etch,” particularly in technical terms like “etch”/“etching” describing fabrication processes.

    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
     да
    -0.07
     persuaded
    -0.07
    InRange
    -0.06
    Inlining
    -0.06
    _mpi
    -0.06
    (coeff
    -0.06
     dazu
    -0.06
    Formula
    -0.06
     Мал
    -0.06
    Boot
    -0.06
    POSITIVE LOGITS
     neoliberal
    0.08
     Nelson
    0.06
    JJ
    0.06
     EMS
    0.06
     Effects
    0.06
     EG
    0.06
     Interpret
    0.06
    .Job
    0.06
    ]*)
    0.06
    JT
    0.06
    Activations Density 0.003%

    No Known Activations