© 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. 41003
    Prev
    Next
    INDEX
    Explanations

    elements related to marine life and diving experiences

    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
    ycop
    -0.06
    folk
    -0.06
    azz
    -0.06
    unos
    -0.06
     cyk
    -0.06
    cki
    -0.06
     lidi
    -0.06
    upe
    -0.06
    .Temp
    -0.06
     Hij
    -0.05
    POSITIVE LOGITS
     depending
    0.09
     Depending
    0.08
    depending
    0.07
    Depending
    0.07
     tod
    0.07
     our
    0.07
    apro
    0.07
     we
    0.07
    opro
    0.07
     dependent
    0.07
    Activations Density 0.007%

    No Known Activations