© 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. 15-LLAMASCOPE-RES-131K
    6. 90318
    Prev
    Next
    INDEX
    Explanations

    terms related to natural resources and environmental sustainability

    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
     Decompiled
    -0.07
    coil
    -0.07
     luder
    -0.06
     Roose
    -0.06
    áty
    -0.06
    .FLAG
    -0.06
    /lg
    -0.06
     SIMD
    -0.06
    stag
    -0.06
     pohod
    -0.06
    POSITIVE LOGITS
     Natural
    0.17
     natural
    0.17
    Natural
    0.16
    natural
    0.14
    atural
    0.12
     naturally
    0.11
    èĩªçĦ¶
    0.11
     doÄŁal
    0.10
     NAT
    0.09
     unnatural
    0.09
    Activations Density 0.044%

    No Known Activations