© 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. 129100
    Prev
    Next
    INDEX
    Explanations

    mentions of various groups of people and their roles or activities

    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
    acho
    -0.07
     огÑĢа
    -0.07
    389
    -0.07
    ilis
    -0.06
     factorial
    -0.06
    lassen
    -0.06
    ego
    -0.06
    овиÑĩ
    -0.06
    olid
    -0.06
     вог
    -0.06
    POSITIVE LOGITS
     convers
    0.07
    ussian
    0.06
    ž
    0.06
    -danger
    0.06
    ertiary
    0.06
    ippers
    0.06
     preparing
    0.06
     anale
    0.06
     Schmidt
    0.06
    å¾
    0.06
    Activations Density 0.021%

    No Known Activations