© 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 EvalsExportsinterp-engineNEWAPI 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. 58981
    Prev
    Next
    INDEX
    Explanations

    -pre

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of on-premise deployment (e.g., “on-premise,” “premises”) in the 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
    <?,
    -0.06
    τού
    -0.06
     Fare
    -0.06
    /conf
    -0.06
    dou
    -0.06
    Store
    -0.06
     Lobby
    -0.06
    GreaterThan
    -0.06
     octave
    -0.06
    acos
    -0.06
    POSITIVE LOGITS
    .getResources
    0.07
     constellation
    0.07
    .LayoutInflater
    0.06
     ne
    0.06
     khắc
    0.06
     bait
    0.06
    /portfolio
    0.06
    θυν
    0.06
    (chart
    0.06
     cravings
    0.06
    Activations Density 0.008%

    No Known Activations