© 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. 9-LLAMASCOPE-RES-131K
    11. 94268
    Prev
    Next
    INDEX
    Explanations

    references to "one" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    kowski
    -0.08
    shan
    -0.07
    rypton
    -0.07
    abei
    -0.07
    oningen
    -0.07
    .scalablytyped
    -0.06
    neider
    -0.06
    lsru
    -0.06
    aktiv
    -0.06
    ovi
    -0.06
    POSITIVE LOGITS
     Reef
    0.07
     Rockefeller
    0.06
    EFR
    0.06
    TPL
    0.06
    ØŃد
    0.06
    кÑĢаÑĹ
    0.06
    áno
    0.06
    ÑĢÑĸÑĩ
    0.06
    apy
    0.06
    ãģĸ
    0.06
    Activations Density 0.010%

    No Known Activations