© 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. 83805
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistics

    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
    ÇIJ
    -0.07
    ÏĬ
    -0.06
    клÑİÑĩ
    -0.06
    δή
    -0.06
    elia
    -0.06
     Counts
    -0.06
    кол
    -0.06
    yst
    -0.06
     unto
    -0.05
    andle
    -0.05
    POSITIVE LOGITS
     total
    0.10
     possible
    0.08
    .total
    0.08
    -total
    0.08
    total
    0.08
     available
    0.07
    possible
    0.07
     altogether
    0.07
     ones
    0.07
     возмож
    0.07
    Activations Density 0.022%

    No Known Activations