© 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. 75305
    Prev
    Next
    INDEX
    Explanations

    references to retreats or similar gatherings

    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
    abeth
    -0.08
    xing
    -0.07
    anko
    -0.07
    ãģĦãĤĭ
    -0.07
    itored
    -0.07
    alet
    -0.07
    cio
    -0.07
    erland
    -0.07
    serter
    -0.06
    phans
    -0.06
    POSITIVE LOGITS
    ively
    0.09
    ive
    0.09
    orative
    0.08
    ear
    0.07
    ee
    0.07
    -style
    0.07
    angular
    0.07
    aspect
    0.07
    ary
    0.07
    /release
    0.07
    Activations Density 0.007%

    No Known Activations