© 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. 15-LLAMASCOPE-RES-131K
    11. 89539
    Prev
    Next
    INDEX
    Explanations

    terms related to technology and storage solutions

    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
    deo
    -0.09
    /Dk
    -0.07
    .scalablytyped
    -0.07
    omik
    -0.07
    ZONE
    -0.07
    ako
    -0.07
    .mx
    -0.07
    ساÙĨÛĮ
    -0.07
    ÑĦеÑĢ
    -0.07
    sen
    -0.07
    POSITIVE LOGITS
    ³
    0.08
    raquo
    0.06
    097
    0.06
    lace
    0.06
    OKIE
    0.06
    tro
    0.06
    ote
    0.05
    umo
    0.05
    arget
    0.05
    aus
    0.05
    Activations Density 0.001%

    No Known Activations