© 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. 126994
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    The neuron tends to light up on numeric literals in code—integers or floating-point constants wherever they appear.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    code-related terms primarily associated with programming and software development.

    oai_token-act-pair · gpt-4o-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
     dependencies
    -0.07
    here
    -0.07
    holes
    -0.06
     holes
    -0.06
    海
    -0.06
     ForCanBeConvertedToForeach
    -0.06
    .mapper
    -0.06
    ではなく
    -0.06
     exits
    -0.06
    _m
    -0.06
    POSITIVE LOGITS
     Pornhub
    0.07
     banc
    0.06
    사람
    0.06
     GFP
    0.06
     jogador
    0.06
     Civil
    0.06
    ểm
    0.06
    develop
    0.06
     anonymously
    0.06
    ター
    0.06
    Activations Density 0.111%

    No Known Activations