© 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. 91530
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate conditional or structured arrangements

    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
    hurst
    -0.08
    HQ
    -0.08
    eÄį
    -0.08
    ulumi
    -0.07
    inness
    -0.07
    postalcode
    -0.07
    ../../../../
    -0.07
    нина
    -0.07
     lÃłng
    -0.07
    pedia
    -0.07
    POSITIVE LOGITS
     basis
    0.08
    713
    0.07
     McDon
    0.07
    LEN
    0.07
     scale
    0.06
    basis
    0.06
     level
    0.06
     storytelling
    0.06
    oc
    0.06
     strengths
    0.06
    Activations Density 0.009%

    No Known Activations