© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 56409
    Prev
    Next
    INDEX
    Explanations

    free software source

    np_max-act · gemini-2.0-flash

    This neuron flags mentions of free or open-source software (i.e. occurrences of “free software,” “open source,” “software libre,” etc.).

    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
     POLL
    -0.07
     Gat
    -0.06
     domain
    -0.06
     weapon
    -0.06
     weapons
    -0.06
     gắng
    -0.06
     Accessories
    -0.06
     sieve
    -0.06
    hari
    -0.06
     thường
    -0.06
    POSITIVE LOGITS
    _numeric
    0.07
    籍
    0.06
    ตำแหน
    0.06
     Fees
    0.06
    ,sum
    0.06
    _bug
    0.06
    _deriv
    0.06
    .text
    0.06
    ,:)
    0.06
    _click
    0.06
    Activations Density 0.010%

    No Known Activations