© 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. 91537
    Prev
    Next
    INDEX
    Explanations

    directional indicators and spatial references

    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
    icer
    -0.08
    ollo
    -0.07
    лад
    -0.07
    lopedia
    -0.07
    presso
    -0.07
    _INITIALIZER
    -0.07
    arel
    -0.07
    à¥įतà¤ķ
    -0.07
    μβ
    -0.07
    otos
    -0.07
    POSITIVE LOGITS
    AGES
    0.06
     timing
    0.06
    panied
    0.06
    /by
    0.06
     binge
    0.06
     consulting
    0.05
    /left
    0.05
    ages
    0.05
    orraine
    0.05
    most
    0.05
    Activations Density 0.001%

    No Known Activations