© 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. 69794
    Prev
    Next
    INDEX
    Explanations

    HTML and CSS structure elements used in web design

    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
    ream
    -0.07
    bsolute
    -0.07
     covering
    -0.06
    sko
    -0.06
     Lem
    -0.06
    iams
    -0.06
    badge
    -0.06
    oriously
    -0.06
    _bm
    -0.06
    tainment
    -0.06
    POSITIVE LOGITS
    uhn
    0.08
     hát
    0.07
    -fluid
    0.07
    upp
    0.07
    -headed
    0.06
    дина
    0.06
     Fare
    0.06
    LiveData
    0.06
     relic
    0.06
    ORK
    0.06
    Activations Density 0.003%

    No Known Activations