© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 31715
    Prev
    Next
    INDEX
    Explanations

    dates and months

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    IPH
    -0.07
    Åĵ
    -0.07
    vid
    -0.06
    bard
    -0.06
    .SIG
    -0.06
    urge
    -0.06
    igma
    -0.06
    dge
    -0.06
    tring
    -0.06
    ruta
    -0.06
    POSITIVE LOGITS
    ynamo
    0.06
    878
    0.06
    677
    0.06
    kit
    0.06
    ENOMEM
    0.06
    ÏĦÏģα
    0.06
    adiens
    0.06
    oplevel
    0.06
    &T
    0.06
    676
    0.06
    Activations Density 0.112%

    No Known Activations