© 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. 4924
    Prev
    Next
    INDEX
    Explanations

    proper nouns and significant names related to academic and professional works

    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
    abaj
    -0.07
    utut
    -0.07
    æį
    -0.07
    .Selenium
    -0.07
     Roose
    -0.06
    anganese
    -0.06
    åĮħ
    -0.06
    dit
    -0.06
    ENN
    -0.06
    -IS
    -0.06
    POSITIVE LOGITS
    oppel
    0.06
    ties
    0.06
     Hess
    0.06
     furthermore
    0.06
    ietf
    0.06
    821
    0.06
     Cup
    0.05
     ere
    0.05
    abbreviation
    0.05
    IEL
    0.05
    Activations Density 0.060%

    No Known Activations