© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 124464
    Prev
    Next
    INDEX
    Explanations

    references to journalism and news organizations

    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
    venes
    -0.08
    kehr
    -0.06
    xFFFF
    -0.06
    ataire
    -0.06
    akeup
    -0.06
    ãĥ¬ãĥĥãĥĪ
    -0.06
     Mais
    -0.06
     Heck
    -0.06
     azt
    -0.06
    uate
    -0.06
    POSITIVE LOGITS
    (AP
    0.08
    /AP
    0.07
    /Foundation
    0.07
     AP
    0.07
     fod
    0.06
    Reusable
    0.06
    diet
    0.06
    waters
    0.06
    ASF
    0.06
    esh
    0.06
    Activations Density 0.005%

    No Known Activations