© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 61440
    Prev
    Next
    INDEX
    Explanations

    references to outdoor design ideas or images

    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
    коз
    -0.07
    893
    -0.07
    каз
    -0.06
    еÑģÑĮ
    -0.06
     sẻ
    -0.06
     Kostenlose
    -0.06
     ÑĢеÑģ
    -0.06
     Wikispecies
    -0.06
    اÛĮØ´
    -0.06
    nell
    -0.06
    POSITIVE LOGITS
     rule
    0.07
    zek
    0.06
     lump
    0.06
    SURE
    0.06
     Rule
    0.06
    954
    0.06
     examples
    0.06
     ed
    0.06
    dea
    0.06
     object
    0.06
    Activations Density 0.000%

    No Known Activations