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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96482
    Prev
    Next
    INDEX
    Explanations

    references to specific sports teams or 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
    jo
    -0.07
    neau
    -0.06
    inker
    -0.06
    weigh
    -0.06
     Stella
    -0.06
    arella
    -0.05
    undry
    -0.05
    inst
    -0.05
    esch
    -0.05
    archive
    -0.05
    POSITIVE LOGITS
    GetX
    0.07
    .Sin
    0.07
     Barnett
    0.07
    edback
    0.07
     célib
    0.07
    577
    0.06
    .Side
    0.06
    ÑĤен
    0.06
    alsy
    0.06
    νοÏį
    0.06
    Activations Density 0.017%

    No Known Activations