© 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. 1381
    Prev
    Next
    INDEX
    Explanations

    quantitative metrics or data points related to time, space, and populations

    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
    ubu
    -0.09
     _{}
    -0.08
    ãģ¤ãģ¶
    -0.07
    виÑĩай
    -0.07
    csr
    -0.07
    .predicate
    -0.07
    ê´ij
    -0.07
    unate
    -0.07
    æ®ĸ
    -0.07
    drv
    -0.07
    POSITIVE LOGITS
    cket
    0.06
    lasses
    0.06
     rather
    0.06
     Briggs
    0.06
    claimer
    0.05
     :
    0.05
    éru
    0.05
    :
    0.05
    uais
    0.05
     aspect
    0.05
    Activations Density 0.050%

    No Known Activations