© 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 EvalsExportsinterp-engineNEWAPI 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. 80987
    Prev
    Next
    INDEX
    Explanations

    phrases indicating strong influence or impact on a cultural or entertainment scene

    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
    esso
    -0.07
    iek
    -0.07
    úc
    -0.07
    UGE
    -0.07
    ared
    -0.06
     WG
    -0.06
    oda
    -0.06
    ergus
    -0.06
    uges
    -0.06
    umas
    -0.06
    POSITIVE LOGITS
     world
    0.07
    _Construct
    0.07
     industry
    0.07
     charts
    0.07
     parad
    0.06
     worldwide
    0.06
    yz
    0.06
     hearts
    0.06
    ival
    0.06
    world
    0.06
    Activations Density 0.026%

    No Known Activations