© 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. 87647
    Prev
    Next
    INDEX
    Explanations

    mathematical terms related to bounded domains and their properties

    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
     stub
    -0.07
     leaders
    -0.06
     row
    -0.06
     platform
    -0.05
    ç
    -0.05
     brow
    -0.05
     line
    -0.05
    ordin
    -0.05
     Row
    -0.05
    ysz
    -0.05
    POSITIVE LOGITS
    ùa
    0.08
    criptor
    0.08
    ETYPE
    0.08
     domaine
    0.08
    erus
    0.08
    ắn
    0.08
    irk
    0.07
     volumes
    0.07
    åĮºåŁŁ
    0.07
    éĿ¢ç©į
    0.07
    Activations Density 0.133%

    No Known Activations