© 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. 22-LLAMASCOPE-RES-131K
    11. 3735
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts related to isomorphisms and graph properties

    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
    меÑĩ
    -0.07
    ilerden
    -0.07
    acha
    -0.07
    mite
    -0.07
    illance
    -0.07
    ystate
    -0.07
    ertino
    -0.07
    nim
    -0.06
    yna
    -0.06
    igits
    -0.06
    POSITIVE LOGITS
     recent
    0.08
     recently
    0.08
     Interest
    0.07
     related
    0.07
     interest
    0.07
    Interest
    0.07
    recent
    0.07
    interest
    0.07
     Mot
    0.06
    related
    0.06
    Activations Density 0.095%

    No Known Activations