© 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. 119042
    Prev
    Next
    INDEX
    Explanations

    topics related to global poverty and humanitarian efforts to provide essential resources like clean water

    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
    plode
    -0.07
    pillar
    -0.07
    NIL
    -0.06
     Wet
    -0.06
    arium
    -0.06
     )↵↵↵↵↵↵↵↵
    -0.06
    erse
    -0.06
    ByKey
    -0.06
    TL
    -0.06
    pill
    -0.06
    POSITIVE LOGITS
     worldwide
    0.12
     global
    0.11
     world
    0.10
     overseas
    0.10
    global
    0.10
     Global
    0.09
    åħ¨çIJĥ
    0.09
     abroad
    0.09
     glob
    0.09
     GLOBAL
    0.09
    Activations Density 0.063%

    No Known Activations