© 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. 85492
    Prev
    Next
    INDEX
    Explanations

    terms associated with ranking and positioning in competitive contexts

    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
     Petro
    -0.05
     and
    -0.05
     direct
    -0.05
     tune
    -0.05
     rescue
    -0.05
     circ
    -0.05
     bolt
    -0.05
     Average
    -0.05
    azi
    -0.05
     aspects
    -0.05
    POSITIVE LOGITS
     hierarchy
    0.12
    _hierarchy
    0.10
    heap
    0.10
    priority
    0.10
     ladder
    0.10
     rankings
    0.10
    Hierarchy
    0.10
     charts
    0.10
     heap
    0.10
    梯
    0.10
    Activations Density 0.102%

    No Known Activations