© 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. 107376
    Prev
    Next
    INDEX
    Explanations

    references to scientific concepts and equations

    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
    terra
    -0.07
     inspir
    -0.07
    lator
    -0.06
    vil
    -0.06
     Wire
    -0.06
    Wire
    -0.06
     wiring
    -0.06
     Inspir
    -0.06
     Fly
    -0.06
    ãĥĥãĥĹ
    -0.06
    POSITIVE LOGITS
     incident
    0.08
    å±
    0.08
    /ref
    0.07
     ref
    0.07
    ajs
    0.07
    Cancellation
    0.07
    ãĥ¬ãĥ³
    0.07
    horn
    0.07
     Ey
    0.07
    -ref
    0.07
    Activations Density 0.012%

    No Known Activations