© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 56972
    Prev
    Next
    INDEX
    Explanations

    build

    np_max-act · gemini-2.0-flash

    This neuron detects status‐ and version‐badge labels (e.g. “Build,” “npm,” “version,” “license,” “dependency,” etc.) in README metadata.

    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
    .pt
    -0.07
    .lower
    -0.07
    ']}'
    -0.06
     RoundedRectangle
    -0.06
    (conn
    -0.06
    781
    -0.06
     žen
    -0.06
    rior
    -0.06
    (ti
    -0.06
    SuppressWarnings
    -0.06
    POSITIVE LOGITS
     groot
    0.06
     BEN
    0.06
    .getById
    0.06
     땅
    0.06
    actical
    0.06
    اكم
    0.06
     Cases
    0.06
     canopy
    0.06
    Spread
    0.06
     necessário
    0.05
    Activations Density 0.001%

    No Known Activations