© 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. 60047
    Prev
    Next
    INDEX
    Explanations

    phrases related to results or outcomes

    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
    IDD
    -0.06
     Neal
    -0.06
    âĢª
    -0.06
    ãģĶ
    -0.06
     presence
    -0.06
    ihn
    -0.06
    gın
    -0.06
    ERO
    -0.06
     Needle
    -0.05
    ota
    -0.05
    POSITIVE LOGITS
    ä¸įäºĨ
    0.07
    enez
    0.07
    bek
    0.07
    ÏĥÏį
    0.07
    WithContext
    0.07
    ysize
    0.07
    andas
    0.06
    OrElse
    0.06
    etag
    0.06
    Ú¯ÛĮ
    0.06
    Activations Density 0.006%

    No Known Activations