© 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. 88174
    Prev
    Next
    INDEX
    Explanations

    instances of numeric values within a specific range

    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
    .sprites
    -0.06
    ROME
    -0.06
     Rowe
    -0.06
    ynet
    -0.06
    ere
    -0.06
    isses
    -0.06
    ureka
    -0.06
     Eg
    -0.06
    mtime
    -0.06
    .I
    -0.06
    POSITIVE LOGITS
    uyá»ĩt
    0.07
    mekte
    0.07
    eil
    0.06
    ipeg
    0.06
    äh
    0.06
    ãĥ¼ãĥĵãĤ¹
    0.06
    åĵ¦
    0.06
    γη
    0.06
    adel
    0.06
    istrovstvÃŃ
    0.06
    Activations Density 0.015%

    No Known Activations