© 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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 90878
    Prev
    Next
    INDEX
    Explanations

    terms and identifiers related to user ownership and author information in a software context

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

    Identifiers and properties related to users or ownership in code and structured data formats, often appearing within JSON objects, function parameters, or configuration files.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    achuset
    -0.07
    lems
    -0.07
    .MixedReality
    -0.07
    iston
    -0.07
    atra
    -0.07
    disposed
    -0.07
    atham
    -0.07
    adera
    -0.07
    eket
    -0.07
    offee
    -0.07
    POSITIVE LOGITS
     who
    0.09
     whom
    0.08
     Who
    0.08
    who
    0.07
    Who
    0.07
     person
    0.07
     role
    0.06
     responsible
    0.06
     volunteer
    0.06
    ä¸Ģ人
    0.06
    Activations Density 0.020%

    No Known Activations