© 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. 87194
    Prev
    Next
    INDEX
    Explanations

    references to historical origins and developments

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

    Phrases that establish historical origins or connections between present entities and their past beginnings.

    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
    .AutoComplete
    -0.08
    immel
    -0.07
     pile
    -0.07
    .IsEmpty
    -0.06
    .setProperty
    -0.06
    opak
    -0.06
    creativecommons
    -0.06
    hin
    -0.06
    .shiro
    -0.06
    uce
    -0.06
    POSITIVE LOGITS
     trace
    0.18
     roots
    0.18
    trace
    0.17
     traced
    0.17
     traces
    0.15
     tracing
    0.13
     origins
    0.13
    Trace
    0.13
     Trace
    0.12
     root
    0.12
    Activations Density 0.110%

    No Known Activations