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

    Neuronpedia

    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. 60066
    Prev
    Next
    INDEX
    Explanations

    geographic locations and names

    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
    олеÑĤ
    -0.08
    ä¹ĺ
    -0.07
    zie
    -0.07
     sokak
    -0.07
    ntl
    -0.07
    lom
    -0.07
    Äįer
    -0.06
    áo
    -0.06
    phony
    -0.06
    èķ
    -0.06
    POSITIVE LOGITS
     Cornel
    0.06
     kayn
    0.06
    844
    0.06
    енÑı
    0.06
    unct
    0.06
    383
    0.06
     Elder
    0.06
    thr
    0.06
     wil
    0.05
    åij¼
    0.05
    Activations Density 0.001%

    No Known Activations