© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 77518
    Prev
    Next
    INDEX
    Explanations

    references to organizational structures and roles within communities or societies

    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
    och
    -0.06
    ãĤĪãģı
    -0.06
    able
    -0.06
     Haus
    -0.06
    OVE
    -0.06
     Dit
    -0.06
    _VOID
    -0.06
     tượng
    -0.06
    ãĥĿãĤ¤ãĥ³ãĥĪ
    -0.06
    au
    -0.06
    POSITIVE LOGITS
     regarding
    0.16
     concerning
    0.13
     about
    0.12
     Ñīодо
    0.11
    åħ³äºİ
    0.10
     vá»ģ
    0.10
     Regarding
    0.10
    about
    0.09
     towards
    0.09
     tentang
    0.08
    Activations Density 0.482%

    No Known Activations