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

    Neuronpedia

    Jacobian LensNEW
    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. 56132
    Prev
    Next
    INDEX
    Explanations

    references to memory and cognitive function

    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
    estar
    -0.08
    igi
    -0.07
    ήÏĤ
    -0.07
    uido
    -0.07
    eso
    -0.07
    uter
    -0.07
    orce
    -0.06
    ijľ
    -0.06
    icum
    -0.06
    edeki
    -0.06
    POSITIVE LOGITS
    /memory
    0.11
     memory
    0.11
    -memory
    0.10
     Memory
    0.09
     MEMORY
    0.08
    Memory
    0.08
    .Memory
    0.08
     storage
    0.07
    å¿Ĩ
    0.07
    memory
    0.07
    Activations Density 0.007%

    No Known Activations