© 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 EvalsExportsAPI 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. 58678
    Prev
    Next
    INDEX
    Explanations

    significant words related to quantities and actions

    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
     kvinne
    -0.08
     kå
    -0.08
    /mat
    -0.07
    ilip
    -0.07
     eldre
    -0.07
     nø
    -0.07
     godt
    -0.07
    .za
    -0.07
     voksen
    -0.07
     célib
    -0.07
    POSITIVE LOGITS
     is
    0.06
     ;
    0.06
    ↵
    0.06
    .gdx
    0.06
     \↵
    0.06
    PERT
    0.06
     Scout
    0.05
     Kash
    0.05
    eldom
    0.05
    Thunk
    0.05
    Activations Density 0.002%

    No Known Activations