© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 9-LLAMASCOPE-RES-131K
    11. 96313
    Prev
    Next
    INDEX
    Explanations

    keywords related to graduate employment opportunities and apprenticeships

    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
    aliz
    -0.08
    бина
    -0.08
    unger
    -0.07
    ÙģتÙħ
    -0.07
    åłĤ
    -0.07
    illis
    -0.07
    ednou
    -0.07
    esini
    -0.07
    ifu
    -0.06
    redients
    -0.06
    POSITIVE LOGITS
     Dans
    0.06
     Prot
    0.06
     Hazel
    0.06
     tran
    0.06
    Stuff
    0.05
    iki
    0.05
    ornado
    0.05
    .cgi
    0.05
    116
    0.05
    omm
    0.05
    Activations Density 0.013%

    No Known Activations