© 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. 126619
    Prev
    Next
    INDEX
    Explanations

    references to music artists and their accomplishments

    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
    askell
    -0.07
    Solar
    -0.07
    xe
    -0.07
     Rockies
    -0.06
    irut
    -0.06
     Manit
    -0.06
    Steel
    -0.06
     Babe
    -0.06
    loha
    -0.06
     solar
    -0.06
    POSITIVE LOGITS
     London
    0.09
    London
    0.07
     British
    0.07
     UK
    0.07
     london
    0.06
    etri
    0.06
    etto
    0.06
     Telegraph
    0.06
     Jewish
    0.06
     BBC
    0.06
    Activations Density 0.001%

    No Known Activations