© 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. 87893
    Prev
    Next
    INDEX
    Explanations

    references to films, documentaries, and related media

    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
    roe
    -0.07
     routine
    -0.07
    عÙģ
    -0.06
     ubiquitous
    -0.06
     Routine
    -0.06
    routine
    -0.06
    tesy
    -0.06
    иÑģÑĮ
    -0.06
     judging
    -0.06
    ÐķС
    -0.06
    POSITIVE LOGITS
     project
    0.12
     grand
    0.11
     Project
    0.09
    project
    0.09
     completion
    0.09
     Grand
    0.09
     epic
    0.09
     Completion
    0.09
    Project
    0.09
     ambitious
    0.09
    Activations Density 0.130%

    No Known Activations