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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9473
    Prev
    Next
    INDEX
    Explanations

    mass spectrometry

    np_max-act · gemini-2.0-flash

    technical terms and phrases related to mass spectrometry and analytical chemistry methods.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects specialized technical terms describing methods and apparatus in mass spectrometry (e.g. supersonic molecular beams, thermal vaporization, spray formation, ionization nozzles).

    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
    öy
    -0.07
    -sidebar
    -0.07
    ¨ط
    -0.06
    wi
    -0.06
    STRACT
    -0.06
     skipped
    -0.06
    只有
    -0.06
    rido
    -0.06
    ерами
    -0.06
    Workers
    -0.06
    POSITIVE LOGITS
    _Path
    0.06
    cov
    0.06
    $temp
    0.06
     dbContext
    0.06
    \Persistence
    0.06
     assessments
    0.06
    ीत
    0.06
     partnerships
    0.06
     foot
    0.06
    ж
    0.06
    Activations Density 0.011%

    No Known Activations