© 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. 3961
    Prev
    Next
    INDEX
    Explanations

    references to countries and their economies

    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
    _RST
    -0.07
    etooth
    -0.07
    νÏĦ
    -0.07
    สาร
    -0.07
    кав
    -0.07
    .bits
    -0.06
    buah
    -0.06
    edla
    -0.06
    engeance
    -0.06
    .IContainer
    -0.06
    POSITIVE LOGITS
    orman
    0.07
     recent
    0.07
     rank
    0.07
     constitution
    0.06
    recent
    0.06
    annel
    0.06
     churn
    0.06
    orm
    0.06
     se
    0.06
     blank
    0.06
    Activations Density 0.018%

    No Known Activations