© 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. 55524
    Prev
    Next
    INDEX
    Explanations

    technical terms and functions related to data processing and algorithms

    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
     ga
    -0.06
    ouz
    -0.06
    638
    -0.06
    uv
    -0.06
     Depends
    -0.06
    çĤ
    -0.06
     vern
    -0.06
    ικο
    -0.06
     spect
    -0.06
    UV
    -0.06
    POSITIVE LOGITS
     input
    0.10
    input
    0.09
     dataset
    0.09
     Input
    0.09
    _input
    0.08
    .dataset
    0.08
     source
    0.08
     SOURCE
    0.08
     inputs
    0.08
    dataset
    0.08
    Activations Density 0.263%

    No Known Activations