© 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. 118660
    Prev
    Next
    INDEX
    Explanations

    mentions of information technology

    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
    istrovstvÃŃ
    -0.07
    Dispatch
    -0.07
    اÙĤ
    -0.07
    adin
    -0.07
    ields
    -0.06
    kowski
    -0.06
    ERY
    -0.06
    pton
    -0.06
    _DECREF
    -0.06
    bestos
    -0.06
    POSITIVE LOGITS
    al
    0.07
    SystemService
    0.06
    rp
    0.06
    /library
    0.06
    als
    0.06
    edList
    0.06
    ally
    0.06
     Retrie
    0.06
    bee
    0.06
     Millennium
    0.06
    Activations Density 0.014%

    No Known Activations