© 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. 3515
    Prev
    Next
    INDEX
    Explanations

    mentions of specific types of memory and storage technology

    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
    ema
    -0.08
    ervo
    -0.07
    upertino
    -0.07
    ाà¤ĩस
    -0.07
     Marino
    -0.07
    çĨ
    -0.07
     sayıda
    -0.07
    amak
    -0.07
    inel
    -0.06
    ocoa
    -0.06
    POSITIVE LOGITS
     memory
    0.07
    lish
    0.07
    ige
    0.06
    .TYPE
    0.06
    /cache
    0.06
     Memory
    0.06
    lli
    0.06
     Overs
    0.06
     Roof
    0.06
    itan
    0.06
    Activations Density 0.001%

    No Known Activations