© 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. 104597
    Prev
    Next
    INDEX
    Explanations

    concepts related to scientific integration and exploration

    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
    /browse
    -0.07
     amb
    -0.07
    .Reader
    -0.06
    esda
    -0.06
    .shapes
    -0.06
     Ñģов
    -0.06
     Edison
    -0.06
    çľ¾
    -0.06
    .Sdk
    -0.06
     peri
    -0.06
    POSITIVE LOGITS
     Universe
    0.08
    nano
    0.07
    icio
    0.07
    zept
    0.06
    rodu
    0.06
    tiny
    0.06
    ctal
    0.06
    agens
    0.06
     Universal
    0.06
     Matter
    0.06
    Activations Density 0.003%

    No Known Activations