© 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. 89421
    Prev
    Next
    INDEX
    Explanations

    references to major reports or significant events

    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
    plib
    -0.07
    ories
    -0.07
    èĦ
    -0.06
     plu
    -0.06
    IDO
    -0.06
    ãĥ³ãĥĸ
    -0.06
    ören
    -0.06
    Percent
    -0.06
    _lowercase
    -0.06
    bote
    -0.06
    POSITIVE LOGITS
     half
    0.08
    çīĪ
    0.07
    half
    0.07
     version
    0.07
    -phase
    0.06
    auc
    0.06
    ilk
    0.06
    erif
    0.06
    inded
    0.06
     two
    0.06
    Activations Density 0.042%

    No Known Activations