© 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 EvalsExportsinterp-engineNEWAPI 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. 42371
    Prev
    Next
    INDEX
    Explanations

    programming and technical jargon related to memory management

    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
     tonumber
    -0.06
    rego
    -0.06
    awah
    -0.06
    ppo
    -0.06
    -fields
    -0.05
    аÑĢи
    -0.05
    Ether
    -0.05
    uples
    -0.05
     Wo
    -0.05
     Archer
    -0.05
    POSITIVE LOGITS
    blas
    0.07
    ãĥ³ãĥĹ
    0.07
    ReuseIdentifier
    0.07
     Fort
    0.07
    GRAM
    0.07
    gettext
    0.07
     Gram
    0.06
     QR
    0.06
    .react
    0.06
     fort
    0.06
    Activations Density 0.008%

    No Known Activations