© 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. 78506
    Prev
    Next
    INDEX
    Explanations

    references to URLs and related technical terms in a context of data retrieval and processing

    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
    742
    -0.07
    رÛĮاÙĨ
    -0.07
    fts
    -0.07
    ÅĻi
    -0.06
    ",__
    -0.06
     Dam
    -0.06
    <message
    -0.06
     ngắn
    -0.06
    Defaults
    -0.06
     herd
    -0.06
    POSITIVE LOGITS
     hidden
    0.08
    hidden
    0.07
    _hidden
    0.07
     visible
    0.06
     Hidden
    0.06
    ARA
    0.06
     structure
    0.06
     Trot
    0.06
    yd
    0.06
    ulfilled
    0.06
    Activations Density 0.007%

    No Known Activations