© 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. 74811
    Prev
    Next
    INDEX
    Explanations

    descriptive terms related to deserts and landscapes

    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
    lish
    -0.07
     Salmon
    -0.06
     Rousse
    -0.06
     леÑģ
    -0.06
     Snowden
    -0.06
    ningen
    -0.06
    phoon
    -0.06
    uguay
    -0.06
    Overflow
    -0.06
     Sylv
    -0.06
    POSITIVE LOGITS
     desert
    0.22
     Desert
    0.22
     Tucson
    0.13
     Sahara
    0.13
     Arizona
    0.12
     sand
    0.12
     Oasis
    0.11
     sands
    0.11
    Arizona
    0.11
     Sands
    0.11
    Activations Density 0.307%

    No Known Activations