© 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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 118754
    Prev
    Next
    INDEX
    Explanations

    terms related to business and technology impacts, particularly those affecting employment and work dynamics

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

    Common transition or connecting words that link ideas, introduce examples, or create flow between different parts of the text.

    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
    iesel
    -0.07
    Äįet
    -0.07
    /tty
    -0.07
    ethyst
    -0.07
    GuidId
    -0.07
    ermann
    -0.07
    osis
    -0.07
     Kramer
    -0.06
    tober
    -0.06
     Weiss
    -0.06
    POSITIVE LOGITS
    eni
    0.07
    enic
    0.06
    ĸ
    0.06
     Ner
    0.06
    abal
    0.06
     rec
    0.06
    VG
    0.06
    θι
    0.06
     cong
    0.05
    umi
    0.05
    Activations Density 0.011%

    No Known Activations