© 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. 6220
    Prev
    Next
    INDEX
    Explanations

    inclusion

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of statistical modeling and analysis methods (e.g. regression, stepwise model building, and related terminology).

    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
    mon
    -0.06
    lying
    -0.06
    .fhir
    -0.06
    ۱۲
    -0.06
     McKay
    -0.06
     minHeight
    -0.06
    hasil
    -0.06
    .levels
    -0.06
    9
    -0.06
    (instr
    -0.05
    POSITIVE LOGITS
    の
    0.07
     продукції
    0.07
    Trim
    0.06
    _adv
    0.06
    antidad
    0.06
    Scott
    0.06
    aida
    0.06
    _met
    0.06
    userService
    0.06
    λικ
    0.06
    Activations Density 0.013%

    No Known Activations