© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 127864
    Prev
    Next
    INDEX
    Explanations

    references to specific bands and their attributes

    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
     himself
    -0.11
     solo
    -0.09
     Solo
    -0.09
     his
    -0.08
    his
    -0.08
    Solo
    -0.08
    ä»ĸçļĦ
    -0.07
     hers
    -0.07
    .uc
    -0.07
    uet
    -0.06
    POSITIVE LOGITS
     themselves
    0.13
     their
    0.12
     Their
    0.11
    Their
    0.11
    their
    0.10
     members
    0.09
    members
    0.09
     leur
    0.09
     yourselves
    0.08
     иÑħ
    0.08
    Activations Density 0.168%

    No Known Activations