© 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. 27385
    Prev
    Next
    INDEX
    Explanations

    industry-related terms and the dynamics of talent acquisition in entertainment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    iae
    -0.07
    itia
    -0.06
    ilden
    -0.06
    CallCheck
    -0.06
    acus
    -0.06
    eyse
    -0.06
    GuidId
    -0.06
    ameda
    -0.06
    ucci
    -0.06
     rekl
    -0.06
    POSITIVE LOGITS
     Reject
    0.07
     rejection
    0.07
     receptive
    0.07
     appropri
    0.07
    ruž
    0.06
     reject
    0.06
    .Feature
    0.06
    icy
    0.06
    جÙĪ
    0.06
    UnitTest
    0.06
    Activations Density 0.034%

    No Known Activations