© 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. 594
    Prev
    Next
    INDEX
    Explanations

    phrases related to expectations or actions that follow a structure

    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
    TouchUpInside
    -0.08
    rence
    -0.07
    umba
    -0.07
    TestFixture
    -0.07
    porte
    -0.06
    theid
    -0.06
    iyat
    -0.06
    udad
    -0.06
    út
    -0.06
    reff
    -0.06
    POSITIVE LOGITS
     Slee
    0.07
    à¥įवव
    0.06
    USES
    0.06
    nez
    0.06
    uses
    0.06
    isha
    0.06
     watch
    0.06
    plex
    0.06
    çľī
    0.06
    hin
    0.05
    Activations Density 0.017%

    No Known Activations