© 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. 123258
    Prev
    Next
    INDEX
    Explanations

    references to software licenses and documentation

    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
     --
    -0.07
    elt
    -0.06
     rem
    -0.06
    2
    -0.06
    HA
    -0.06
     ,
    -0.06
     Rom
    -0.06
     pun
    -0.05
    1
    -0.05
    786
    -0.05
    POSITIVE LOGITS
    :])
    0.08
     OTHERWISE
    0.08
    ettel
    0.07
    alsy
    0.07
    HandlerContext
    0.07
    éĺħ读次æķ°
    0.07
    elas
    0.07
    indo
    0.07
    wnd
    0.07
    turnstile
    0.07
    Activations Density 0.001%

    No Known Activations