© 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. 38469
    Prev
    Next
    INDEX
    Explanations

    information related to organized groups or collections

    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
    Å¡ka
    -0.06
    ãĤ±ãĥĥãĥĪ
    -0.06
    cházÃŃ
    -0.06
    AUSE
    -0.06
     respectively
    -0.06
    immel
    -0.06
     dabei
    -0.06
    ernational
    -0.06
    å°¤
    -0.06
    anzi
    -0.05
    POSITIVE LOGITS
     other
    0.27
    other
    0.22
    åħ¶ä»ĸ
    0.19
    -other
    0.18
     Other
    0.18
     autres
    0.18
    (other
    0.18
    Other
    0.18
     otras
    0.18
     altre
    0.18
    Activations Density 0.058%

    No Known Activations