© 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 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. 71353
    Prev
    Next
    INDEX
    Explanations

    elements of digital image organization and metadata

    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
    aucoup
    -0.07
     Kauf
    -0.06
    owan
    -0.06
    kontakte
    -0.06
     monopol
    -0.06
    \b
    -0.06
    лÑĥÑĩ
    -0.06
    oup
    -0.06
    deal
    -0.06
    lady
    -0.06
    POSITIVE LOGITS
     accompanying
    0.15
     caption
    0.14
     captions
    0.14
     accompany
    0.13
     metadata
    0.12
     commentary
    0.12
     accompanies
    0.12
     accompagn
    0.12
    .metadata
    0.12
     annotation
    0.11
    Activations Density 0.188%

    No Known Activations