© 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. 89863
    Prev
    Next
    INDEX
    Explanations

    references to collaborative and community-focused projects and initiatives

    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
    YG
    -0.06
    vale
    -0.06
    VOID
    -0.06
    Matchers
    -0.06
    chter
    -0.06
     trou
    -0.06
    /Index
    -0.06
    LLLL
    -0.06
    stag
    -0.06
    cro
    -0.06
    POSITIVE LOGITS
     projects
    0.09
    init
    0.08
     initiatives
    0.08
    oproject
    0.07
    projects
    0.07
     init
    0.07
     proj
    0.07
    /init
    0.07
    /projects
    0.07
    Projects
    0.07
    Activations Density 0.020%

    No Known Activations