© 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. 56583
    Prev
    Next
    INDEX
    Explanations

    phrases related to social issues and community support systems

    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
    IRR
    -0.07
     Wrong
    -0.06
    OfType
    -0.06
    etur
    -0.06
    ÑĢог
    -0.06
    оби
    -0.06
    ikel
    -0.06
    apt
    -0.06
    ãĥ¶
    -0.06
     unto
    -0.06
    POSITIVE LOGITS
     inability
    0.12
    æĹłæ³ķ
    0.11
     unable
    0.10
     absence
    0.10
    unable
    0.09
     otherwise
    0.09
     Unable
    0.09
     cannot
    0.09
     lack
    0.09
     imposs
    0.09
    Activations Density 0.076%

    No Known Activations