© 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. 15-LLAMASCOPE-RES-131K
    11. 86228
    Prev
    Next
    INDEX
    Explanations

    actions and interactions indicating developments or changes in situations

    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
     èŤ
    -0.07
    imd
    -0.06
     until
    -0.06
     never
    -0.06
    oi
    -0.06
     Gh
    -0.06
    leta
    -0.06
     who
    -0.06
     if
    -0.06
    ens
    -0.06
    POSITIVE LOGITS
     thì
    0.09
     _______,
    0.08
    755
    0.08
     ÑģÑĤало
    0.08
    574
    0.08
     оÑĩеÑĢед
    0.07
    (""),
    0.07
     "=",
    0.07
    ypy
    0.07
    575
    0.07
    Activations Density 0.054%

    No Known Activations