© 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. 5-LLAMASCOPE-RES-131K
    11. 127010
    Prev
    Next
    INDEX
    Explanations

    names of famous musicians and artists

    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
    ãi
    -0.06
    ké
    -0.06
    dan
    -0.06
     GRAT
    -0.06
    lej
    -0.06
    лаÑĩ
    -0.06
     principal
    -0.06
    erator
    -0.06
    etch
    -0.06
    anders
    -0.06
    POSITIVE LOGITS
    ãģ®ãĤĤ
    0.07
    idget
    0.06
    alin
    0.06
    SO
    0.06
     Edwards
    0.06
    RPC
    0.06
    yne
    0.06
    UME
    0.06
    nas
    0.06
    .scalablytyped
    0.06
    Activations Density 0.001%

    No Known Activations