© 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. 17-LLAMASCOPE-RES-131K
    11. 82152
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate economic or industry-related themes

    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
     therefore
    -0.07
     indeed
    -0.07
     thus
    -0.07
     hence
    -0.06
    ï
    -0.06
    thus
    -0.06
     Indeed
    -0.06
    xC
    -0.06
     accordingly
    -0.06
    Ãłi
    -0.06
    POSITIVE LOGITS
    tiv
    0.09
    tual
    0.07
    acer
    0.07
    ledon
    0.07
    ypi
    0.07
    inton
    0.07
    ivent
    0.07
    tul
    0.07
    YPRE
    0.07
    immel
    0.07
    Activations Density 0.023%

    No Known Activations