© 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 EvalsExportsinterp-engineNEWAPI 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. 18297
    Prev
    Next
    INDEX
    Explanations

    themes related to hope and community efforts in social change

    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
    lyn
    -0.07
    geois
    -0.06
    nze
    -0.06
    olio
    -0.06
    wyn
    -0.06
    hl
    -0.06
    icher
    -0.06
    нд
    -0.06
    nez
    -0.06
    idget
    -0.06
    POSITIVE LOGITS
     verv
    0.07
    iss
    0.07
    ops
    0.06
    ipar
    0.06
    "+"
    0.06
    oriously
    0.06
    ãģªãģ®
    0.06
    	TokenName
    0.06
     ()->
    0.06
     moci
    0.05
    Activations Density 0.001%

    No Known Activations