© 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. 82294
    Prev
    Next
    INDEX
    Explanations

    references to API endpoints and related programming elements

    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
    umo
    -0.07
    470
    -0.06
     crews
    -0.06
    andas
    -0.06
    až
    -0.06
    atz
    -0.06
    -at
    -0.06
    rgan
    -0.06
     Edwards
    -0.06
    ancy
    -0.06
    POSITIVE LOGITS
    entions
    0.07
    .ObjectMeta
    0.07
    illisecond
    0.07
    izzato
    0.06
    ालà¤ķ
    0.06
    uchen
    0.06
    ioneer
    0.06
    ialis
    0.06
     toJson
    0.06
    riday
    0.06
    Activations Density 0.003%

    No Known Activations