© 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. 60896
    Prev
    Next
    INDEX
    Explanations

    references to minimal quantities or small groups in various contexts

    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
    atk
    -0.07
    heten
    -0.06
     stuff
    -0.06
    357
    -0.06
    izar
    -0.06
    egin
    -0.06
    806
    -0.06
    iram
    -0.06
    efa
    -0.06
     же
    -0.06
    POSITIVE LOGITS
     few
    0.09
     dozen
    0.09
    few
    0.08
    åĩł
    0.08
    åĩłä¸ª
    0.08
    apol
    0.08
     handful
    0.07
     паÑĢÑĥ
    0.07
    lenme
    0.07
    spi
    0.07
    Activations Density 0.052%

    No Known Activations