© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 76334
    Prev
    Next
    INDEX
    Explanations

    references to accountability and health-related topics

    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
     modern
    -0.06
    yne
    -0.06
     Emer
    -0.06
    ama
    -0.06
     spo
    -0.06
    ãĥĥãĥĦ
    -0.06
    ick
    -0.06
    achel
    -0.06
    ейÑģÑĤв
    -0.06
    lest
    -0.05
    POSITIVE LOGITS
     now
    0.32
     Now
    0.27
    now
    0.27
     ÑĤепеÑĢÑĮ
    0.24
    Now
    0.24
     ahora
    0.24
    _now
    0.23
     NOW
    0.23
    -now
    0.22
     agora
    0.22
    Activations Density 0.173%

    No Known Activations