© 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. 89190
    Prev
    Next
    INDEX
    Explanations

    names of authors and contributors in the text

    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
     vej
    -0.08
    anca
    -0.07
    loth
    -0.07
    nerg
    -0.07
    با
    -0.06
    entai
    -0.06
    noho
    -0.06
    ifest
    -0.06
    iej
    -0.06
    Schedulers
    -0.06
    POSITIVE LOGITS
    ymbol
    0.06
    Router
    0.06
    ä¹ĭä¸Ģ
    0.06
    gabe
    0.06
    IIIK
    0.05
    vine
    0.05
    quan
    0.05
    vro
    0.05
    router
    0.05
    ft
    0.05
    Activations Density 0.032%

    No Known Activations