© 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. 108963
    Prev
    Next
    INDEX
    Explanations

    ix

    np_max-act · gemini-2.0-flash

    configuration-related terms and concepts associated with the NixOS system.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron activates on occurrences of “nix” (e.g. in “nix,” “NixOS,” “nix-shell,” etc.), i.e. references to the Nix ecosystem.

    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
     rowspan
    -0.06
    ίσω
    -0.06
     apt
    -0.06
     touchdown
    -0.06
     first
    -0.06
    bold
    -0.06
    retty
    -0.06
    _attributes
    -0.06
    _quest
    -0.06
     měli
    -0.06
    POSITIVE LOGITS
    grant
    0.08
    새
    0.07
    <[
    0.07
     SEC
    0.07
     BlackBerry
    0.07
    ger
    0.06
     इल
    0.06
     péri
    0.06
    ifie
    0.06
    '",↵
    0.06
    Activations Density 0.002%

    No Known Activations