© 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. 117671
    Prev
    Next
    INDEX
    Explanations

    references to specific economic conditions and policies

    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
     tonight
    -0.07
    oppins
    -0.06
    agus
    -0.06
     dür
    -0.06
     cuckold
    -0.06
    имо
    -0.06
    CHAT
    -0.06
     WHATSOEVER
    -0.06
    itan
    -0.06
    çĴ
    -0.06
    POSITIVE LOGITS
    izr
    0.07
    https
    0.07
     https
    0.06
     stated
    0.06
    ÙģتÙĩ
    0.06
    issy
    0.06
     report
    0.06
    lops
    0.06
    ignum
    0.06
    inkel
    0.06
    Activations Density 0.028%

    No Known Activations