© 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. 123371
    Prev
    Next
    INDEX
    Explanations

    references to online data resources

    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
    iddi
    -0.08
    ovice
    -0.07
    agara
    -0.07
    jde
    -0.07
     Zum
    -0.07
    _rewrite
    -0.07
    illac
    -0.07
    Mono
    -0.07
    eÅŁit
    -0.06
    qli
    -0.06
    POSITIVE LOGITS
     finally
    0.07
     Lib
    0.06
     remainder
    0.06
     FT
    0.06
    Ä°T
    0.06
     oh
    0.06
    oni
    0.06
    ert
    0.06
     Cur
    0.06
    pot
    0.05
    Activations Density 0.000%

    No Known Activations