© 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. 18364
    Prev
    Next
    INDEX
    Explanations

    inquiries about ancient Greek theatre and its elements

    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
    antage
    -0.07
    eca
    -0.05
     âĨIJ
    -0.05
    470
    -0.05
    552
    -0.05
    829
    -0.05
     Immediate
    -0.05
    /IP
    -0.05
    _Width
    -0.05
    elf
    -0.05
    POSITIVE LOGITS
    лиÑĪком
    0.07
    AZY
    0.07
    kem
    0.07
    HQ
    0.07
     endpoints
    0.07
    .nano
    0.07
    οÏįÏĤ
    0.07
     episode
    0.07
    OSE
    0.06
     Undert
    0.06
    Activations Density 0.010%

    No Known Activations