© 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. 85513
    Prev
    Next
    INDEX
    Explanations

    phrases related to renting or leasing services, particularly dumpsters

    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
    bai
    -0.07
    amarin
    -0.07
    ÑĤаÑħ
    -0.07
    andon
    -0.06
    inki
    -0.06
    loys
    -0.06
    bk
    -0.06
    prt
    -0.06
    Imports
    -0.06
    ektir
    -0.06
    POSITIVE LOGITS
    vs
    0.07
     Platform
    0.07
    olson
    0.06
    JE
    0.06
    UrlParser
    0.06
    RG
    0.06
     Cas
    0.06
    .jsdelivr
    0.06
     versus
    0.06
    VS
    0.06
    Activations Density 0.003%

    No Known Activations