© 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. 2912
    Prev
    Next
    INDEX
    Explanations

    HTML elements and structure in a document

    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
    onec
    -0.07
    ë§Ŀ
    -0.07
    -parser
    -0.07
    option
    -0.06
    oft
    -0.06
    hausen
    -0.06
     "%"
    -0.06
    inkle
    -0.06
    udu
    -0.06
    ahat
    -0.06
    POSITIVE LOGITS
    产
    0.06
    aurant
    0.06
    apis
    0.06
    mans
    0.06
    uent
    0.06
     middle
    0.06
    ctxt
    0.05
    é¼
    0.05
     Alv
    0.05
    VEST
    0.05
    Activations Density 0.002%

    No Known Activations