© 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. 70163
    Prev
    Next
    INDEX
    Explanations

    references to specific institutions and entities

    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
    ocab
    -0.09
    endencies
    -0.08
    ennen
    -0.07
    iParam
    -0.07
    -transitional
    -0.07
    .gg
    -0.07
    è³¢
    -0.07
    eÄį
    -0.07
    fillType
    -0.07
    chalk
    -0.07
    POSITIVE LOGITS
     itself
    0.09
     should
    0.06
    atori
    0.06
     Anonymous
    0.06
     leadership
    0.05
     mai
    0.05
    avern
    0.05
    .vs
    0.05
     motto
    0.05
     versus
    0.05
    Activations Density 0.124%

    No Known Activations