© 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. 40323
    Prev
    Next
    INDEX
    Explanations

    queries and questions about locations or circumstances

    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
    OLLOW
    -0.06
    comic
    -0.06
    spin
    -0.06
    lesh
    -0.06
    ola
    -0.06
    éģĵ
    -0.06
    aro
    -0.06
     éģĵ
    -0.06
    loor
    -0.06
    agal
    -0.05
    POSITIVE LOGITS
     located
    0.09
    located
    0.08
    ä½įæĸ¼
    0.08
     resides
    0.08
     exactly
    0.07
     ubic
    0.07
     befind
    0.07
     Located
    0.07
     ÙĤرار
    0.07
     ÙĪاÙĤع
    0.07
    Activations Density 0.148%

    No Known Activations