© 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. 9-LLAMASCOPE-RES-131K
    11. 96315
    Prev
    Next
    INDEX
    Explanations

    technical jargon and concepts related to programming and permissions management

    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
    ael
    -0.07
    ilip
    -0.06
    ae
    -0.06
    ptides
    -0.06
     scenario
    -0.06
    Scenario
    -0.06
    locals
    -0.06
    scenario
    -0.06
    uer
    -0.06
     Fat
    -0.05
    POSITIVE LOGITS
    ocache
    0.08
    pNet
    0.07
    Stars
    0.07
    WSC
    0.07
    ypi
    0.07
    imore
    0.07
    ETA
    0.06
    .CopyTo
    0.06
    oproject
    0.06
     Stars
    0.06
    Activations Density 0.142%

    No Known Activations