© 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. 42653
    Prev
    Next
    INDEX
    Explanations

    nouns related to research studies and scientific investigations

    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
     rather
    -0.06
    stoff
    -0.06
    instanc
    -0.06
    hoe
    -0.06
    ved
    -0.06
    ī´
    -0.06
    spath
    -0.06
     Glass
    -0.05
    createQuery
    -0.05
    uffy
    -0.05
    POSITIVE LOGITS
     ìĿ´ë²Ī
    0.08
    ä¹ĭä¸Ģ
    0.07
     junto
    0.07
     sert
    0.07
    along
    0.07
     è©ķ価
    0.07
    aju
    0.07
    -ST
    0.07
    aint
    0.06
    embro
    0.06
    Activations Density 0.021%

    No Known Activations