© 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. 62774
    Prev
    Next
    INDEX
    Explanations

    key indicators or features related to research and academic membership

    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
    936
    -0.07
    aca
    -0.07
    ÅĪ
    -0.06
     Fowler
    -0.06
    945
    -0.06
    mobx
    -0.06
    LTRB
    -0.06
    맨
    -0.06
    etta
    -0.06
    251
    -0.06
    POSITIVE LOGITS
     âĢ¢
    0.08
    âĢ¢
    0.08
    :↵
    0.07
    _allocator
    0.06
    ãĥ»ãĤ¢
    0.06
    éal
    0.06
    à¹Ħร
    0.06
    âľĶ
    0.06
    rst
    0.06
     ranges
    0.06
    Activations Density 0.042%

    No Known Activations