© 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. 65227
    Prev
    Next
    INDEX
    Explanations

    repository

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of “repository” (and its close variants) in code-related text.

    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
    5
    -0.09
     fits
    -0.08
     scaled
    -0.07
    65
    -0.07
    1
    -0.06
    duced
    -0.06
     sinc
    -0.06
    *sin
    -0.06
    300
    -0.06
    δ
    -0.06
    POSITIVE LOGITS
     repository
    0.12
     repositories
    0.10
    repository
    0.09
    \Repository
    0.08
     Robertson
    0.08
    pu
    0.08
    pen
    0.08
    webElementProperties
    0.08
    repo
    0.08
    .repo
    0.08
    Activations Density 0.007%

    No Known Activations