© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 29036
    Prev
    Next
    INDEX
    Explanations

    terms related to bird behavior and nesting opportunities

    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
    anje
    -0.07
    ź
    -0.07
    acea
    -0.07
    cean
    -0.06
    rets
    -0.06
    åĭĿ
    -0.06
    UniqueId
    -0.06
    raki
    -0.06
     aqu
    -0.06
    811
    -0.06
    POSITIVE LOGITS
     Stealth
    0.06
    ocha
    0.06
    ông
    0.06
     calls
    0.06
    ëł¹
    0.06
     breakthrough
    0.05
     Sonic
    0.05
    важа
    0.05
     Trophy
    0.05
     Richardson
    0.05
    Activations Density 0.003%

    No Known Activations