© 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. 88521
    Prev
    Next
    INDEX
    Explanations

    financial figures and metrics related to contracts and market statistics

    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
    amma
    -0.07
    hq
    -0.06
    etter
    -0.06
    oom
    -0.06
    anner
    -0.06
    esan
    -0.06
    andre
    -0.05
    isbury
    -0.05
     WaitForSeconds
    -0.05
    roup
    -0.05
    POSITIVE LOGITS
     past
    0.11
     years
    0.11
     editions
    0.10
    ë§Īëĭ¤
    0.10
     consecutive
    0.10
     seasons
    0.10
     successive
    0.10
    åİĨ
    0.10
    past
    0.10
     yearly
    0.10
    Activations Density 0.201%

    No Known Activations