© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 27573
    Prev
    Next
    INDEX
    Explanations

    terms related to data management and statistical analysis

    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
    éijij
    -0.07
     libs
    -0.07
     Vá»ĭ
    -0.07
     ngang
    -0.07
    orst
    -0.06
    λή
    -0.06
    çĺ
    -0.06
    ortex
    -0.06
    kaar
    -0.06
     pha
    -0.06
    POSITIVE LOGITS
     data
    0.10
     Data
    0.08
    -data
    0.07
    data
    0.07
    ãĥ³ãĥĩãĤ£
    0.07
     Dataset
    0.07
     dataset
    0.07
    >Data
    0.07
    .data
    0.06
    æķ°æį®
    0.06
    Activations Density 0.010%

    No Known Activations