© 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. 55516
    Prev
    Next
    INDEX
    Explanations

    references to historical events or time periods

    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
    yum
    -0.06
     Squadron
    -0.06
    itel
    -0.06
     reinforcements
    -0.06
    /GPL
    -0.06
    одав
    -0.06
     Cunning
    -0.06
    IRE
    -0.06
    anc
    -0.06
     Pilot
    -0.06
    POSITIVE LOGITS
    avy
    0.07
    andler
    0.07
     strength
    0.06
     pe
    0.06
     force
    0.06
    strength
    0.06
     purch
    0.06
     Gale
    0.06
     training
    0.06
    Strength
    0.06
    Activations Density 0.050%

    No Known Activations