© 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. 40595
    Prev
    Next
    INDEX
    Explanations

    elements related to public events or gatherings

    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
    Äĥng
    -0.08
    æ°ĹãģĮ
    -0.07
    qing
    -0.07
    icho
    -0.06
    rie
    -0.06
    itre
    -0.06
    curring
    -0.06
    ies
    -0.06
    æ³Ĭ
    -0.06
    iese
    -0.06
    POSITIVE LOGITS
     Aval
    0.06
    OPTIONS
    0.06
     Slo
    0.06
     âĨIJ
    0.06
    483
    0.06
    urm
    0.05
    Scope
    0.05
    .@
    0.05
    ìŀ¥
    0.05
    âĢı
    0.05
    Activations Density 0.001%

    No Known Activations