© 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. 17-LLAMASCOPE-RES-131K
    11. 77744
    Prev
    Next
    INDEX
    Explanations

    phrases related to achievements and performances in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    End-of-content markers that appear in web text, typically at the end of titles, filenames, URLs, or where content is truncated before continuing to a new section.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    Enumer
    -0.06
    ira
    -0.06
    pour
    -0.05
    Reuse
    -0.05
    lc
    -0.05
     repl
    -0.05
     f
    -0.05
     Ray
    -0.05
     pseud
    -0.05
     Nunes
    -0.05
    POSITIVE LOGITS
    uters
    0.08
    /sources
    0.07
    ÑĪин
    0.07
    ÑĪкÑĥ
    0.07
    isman
    0.07
     Äįlánek
    0.07
    ÏĥοÏħ
    0.07
     åħ±
    0.07
    .readString
    0.06
    ROTO
    0.06
    Activations Density 0.051%

    No Known Activations