© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 57005
    Prev
    Next
    INDEX
    Explanations

    metrics and performance evaluations related to machine learning datasets

    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
     stri
    -0.06
    ____
    -0.06
    isser
    -0.06
    ens
    -0.06
    æŀļ
    -0.06
    tent
    -0.06
    bove
    -0.05
    串
    -0.05
    ापà¤ķ
    -0.05
     stake
    -0.05
    POSITIVE LOGITS
     dataset
    0.12
    benchmark
    0.10
     Dataset
    0.09
     benchmark
    0.09
    .TestCase
    0.09
     datasets
    0.09
    dataset
    0.08
    .dataset
    0.08
    Dataset
    0.08
    -example
    0.08
    Activations Density 0.090%

    No Known Activations