© 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. 42662
    Prev
    Next
    INDEX
    Explanations

    references to temporal data specifically related to years

    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
     compared
    -0.16
     Compared
    -0.13
     vs
    -0.10
     versus
    -0.09
     compare
    -0.09
    æ¯Ķ
    -0.09
     Vs
    -0.08
     compares
    -0.08
     than
    -0.07
     comparison
    -0.07
    POSITIVE LOGITS
    .scalablytyped
    0.07
    isans
    0.07
    idal
    0.07
    ibal
    0.07
    çļĦåľ°
    0.07
    ilen
    0.07
    adir
    0.07
    Ã¤ÃŁ
    0.06
    太éĥİ
    0.06
    216
    0.06
    Activations Density 0.010%

    No Known Activations