© 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. 1180
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the highest quality or standards

    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
    antu
    -0.07
    kt
    -0.07
    imli
    -0.06
     lá»Ĺ
    -0.06
    than
    -0.06
    cé
    -0.06
    oris
    -0.06
    ãģ£
    -0.06
    iswa
    -0.06
    997
    -0.06
    POSITIVE LOGITS
     imaginable
    0.10
     of
    0.09
     possible
    0.09
     possibile
    0.08
     Possible
    0.08
    possible
    0.08
     posible
    0.07
     possÃŃvel
    0.07
    ãĥ©ãĥĥãĤ¯
    0.07
    Possible
    0.06
    Activations Density 0.018%

    No Known Activations