© 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. 15-LLAMASCOPE-RES-131K
    11. 89875
    Prev
    Next
    INDEX
    Explanations

    references to quality and business-related concepts

    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
    pher
    -0.07
    sen
    -0.07
     Lv
    -0.06
    edom
    -0.06
    sburg
    -0.06
    amel
    -0.06
    egan
    -0.06
     gibi
    -0.06
    zcze
    -0.06
    ExecutionContext
    -0.06
    POSITIVE LOGITS
    wu
    0.06
     Percy
    0.06
    474
    0.06
    wal
    0.06
     Cous
    0.06
     Perry
    0.06
    482
    0.06
    ãĢģé«ĺ
    0.06
    hud
    0.06
    bast
    0.06
    Activations Density 0.008%

    No Known Activations