© 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. 129370
    Prev
    Next
    INDEX
    Explanations

    references to educational programs and opportunities for high school students

    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
     Darwin
    -0.07
    ensi
    -0.07
    åĽ£
    -0.06
    adders
    -0.06
    vely
    -0.06
    å®
    -0.06
    gross
    -0.06
    entai
    -0.06
    onom
    -0.06
    èĩ
    -0.06
    POSITIVE LOGITS
     Transfer
    0.08
    transfer
    0.08
     transfer
    0.08
    -transfer
    0.08
    езÑĥлÑĮÑĤ
    0.07
    WithPath
    0.07
    TRANSFER
    0.07
    Dual
    0.07
    ntax
    0.07
    Transfer
    0.07
    Activations Density 0.024%

    No Known Activations