© 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. 80777
    Prev
    Next
    INDEX
    Explanations

    scientific terminologies and results related to research studies

    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
    ãĥŃãĥ¼
    -0.07
    :///
    -0.07
    zin
    -0.07
    ¶Į
    -0.07
    LETED
    -0.07
     адже
    -0.07
    æ¯ķ
    -0.06
     whom
    -0.06
    ÅĻÃŃzenÃŃ
    -0.06
     sobÄĽ
    -0.06
    POSITIVE LOGITS
     neither
    0.08
     only
    0.07
    ilit
    0.07
    igon
    0.06
    ansion
    0.06
    iger
    0.06
     unexpectedly
    0.06
     Moses
    0.06
     surprisingly
    0.06
    .vec
    0.06
    Activations Density 0.034%

    No Known Activations