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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3794
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to user capabilities and functionalities on a website

    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
    æĤ¨çļĦ
    -0.08
    icularly
    -0.08
    your
    -0.08
     yourself
    -0.07
     your
    -0.07
     YOUR
    -0.07
    ãĤĿ
    -0.07
    μά
    -0.07
    YOUR
    -0.07
    egin
    -0.07
    POSITIVE LOGITS
     certain
    0.11
     Certain
    0.09
    Certain
    0.08
     some
    0.08
     stuff
    0.07
    æŁIJ
    0.07
    XXXX
    0.07
    XXX
    0.07
     several
    0.06
     bestimm
    0.06
    Activations Density 0.037%

    No Known Activations