© 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. 80764
    Prev
    Next
    INDEX
    Explanations

    references to specific locations and actions related to daily life experiences

    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
    ombine
    -0.07
    udiant
    -0.07
    Layer
    -0.07
    ást
    -0.07
    -party
    -0.06
     Layer
    -0.06
     seam
    -0.06
    verte
    -0.06
    hol
    -0.06
    incy
    -0.06
    POSITIVE LOGITS
     Fant
    0.07
    Regular
    0.06
     consistent
    0.06
     fantas
    0.06
     observing
    0.06
    tenant
    0.06
     seen
    0.06
    regular
    0.06
     irregular
    0.06
     Regular
    0.06
    Activations Density 0.003%

    No Known Activations