© 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. 28640
    Prev
    Next
    INDEX
    Explanations

    concepts related to community involvement and support

    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
     worldwide
    -0.07
    /Private
    -0.07
     Worldwide
    -0.06
    ãģ«ãģĭ
    -0.06
     reunion
    -0.06
    èĬ¬
    -0.06
    ayi
    -0.06
    _skb
    -0.06
     vấn
    -0.06
    лаж
    -0.06
    POSITIVE LOGITS
     local
    0.16
    local
    0.14
     community
    0.14
     locally
    0.12
     locals
    0.12
     Local
    0.12
    community
    0.12
     LOCAL
    0.11
    .local
    0.11
    (local
    0.11
    Activations Density 0.027%

    No Known Activations