© 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. 80908
    Prev
    Next
    INDEX
    Explanations

    concepts related to education and innovation

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    azu
    -0.07
    ushman
    -0.06
    aversable
    -0.06
     DAM
    -0.06
     overturn
    -0.06
     ally
    -0.06
    ker
    -0.06
     locality
    -0.06
    acker
    -0.06
    ivel
    -0.06
    POSITIVE LOGITS
    pline
    0.07
    ãĤ¹ãĥĨ
    0.07
    湯
    0.06
    _/
    0.06
    ¶Į
    0.06
     youngsters
    0.06
     ePub
    0.06
     backpage
    0.06
    ittel
    0.06
    .$.
    0.06
    Activations Density 0.017%

    No Known Activations