© 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. 104801
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistics related to properties and financial metrics

    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
    yles
    -0.07
    apult
    -0.07
    azel
    -0.07
    ért
    -0.06
     addButton
    -0.06
    ulumi
    -0.06
    .lex
    -0.06
    ParticleSystem
    -0.06
    flen
    -0.06
    odÃŃ
    -0.06
    POSITIVE LOGITS
    ongo
    0.07
    oy
    0.06
     Innoc
    0.06
    upply
    0.06
    yar
    0.06
    upp
    0.06
    orman
    0.06
    izen
    0.06
    .PerformLayout
    0.06
    ĥ
    0.06
    Activations Density 0.024%

    No Known Activations