© 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. 88229
    Prev
    Next
    INDEX
    Explanations

    terms related to memory and information processing

    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
     sint
    -0.08
    ê·
    -0.06
    大åħ¨
    -0.06
    _ABI
    -0.06
    edeki
    -0.06
    vem
    -0.06
     puck
    -0.06
    δά
    -0.06
    hof
    -0.06
     Decom
    -0.06
    POSITIVE LOGITS
     memory
    0.10
     Memory
    0.09
     storage
    0.09
     Memories
    0.09
     memories
    0.09
     storing
    0.09
     hippoc
    0.08
     memor
    0.08
    -memory
    0.08
    nesia
    0.08
    Activations Density 0.002%

    No Known Activations