© 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. 15-RESID-POST-AA
    11. 92889
    Prev
    Next
    INDEX
    Explanations

    build

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    що
    -0.07
    izzo
    -0.07
     optic
    -0.07
     suspect
    -0.07
     aşağıdaki
    -0.07
    _Node
    -0.07
     cron
    -0.07
     note
    -0.07
     sampled
    -0.06
     サ
    -0.06
    POSITIVE LOGITS
     build
    0.13
     built
    0.12
     Building
    0.11
     building
    0.11
    Build
    0.11
    build
    0.10
     Build
    0.10
     Builder
    0.09
     Built
    0.09
    Built
    0.09
    Activations Density 0.065%

    No Known Activations