© 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. 74559
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to news and media

    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
     hence
    -0.06
    ãĤ¯ãĥŃ
    -0.06
    agara
    -0.06
     ChÃŃ
    -0.06
     ydk
    -0.06
    thus
    -0.06
    decltype
    -0.06
    azi
    -0.06
    LD
    -0.06
     thus
    -0.05
    POSITIVE LOGITS
    wn
    0.08
     ãĤ¹
    0.07
     OT
    0.07
    _Abstract
    0.07
     POT
    0.06
    eph
    0.06
    .ResponseBody
    0.06
    ÂłS
    0.06
    ony
    0.06
    357
    0.06
    Activations Density 0.028%

    No Known Activations