© 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. 69573
    Prev
    Next
    INDEX
    Explanations

    mentions of the Davos summit and related discussions

    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
    ¢
    -0.07
    eras
    -0.06
    asters
    -0.06
    é
    -0.06
     eo
    -0.06
    ulls
    -0.06
    _vlog
    -0.06
    ctl
    -0.06
    ocê
    -0.06
    _PK
    -0.06
    POSITIVE LOGITS
     annual
    0.08
     participant
    0.07
     attendee
    0.07
     world
    0.07
    hotel
    0.07
     jet
    0.06
     summit
    0.06
    ervo
    0.06
     attendees
    0.06
    loquent
    0.06
    Activations Density 0.006%

    No Known Activations