© 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. 82604
    Prev
    Next
    INDEX
    Explanations

    connecting words or phrases that indicate relationships or processes in a narrative

    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
    avana
    -0.07
    edl
    -0.07
    Segoe
    -0.07
    opyright
    -0.07
    aint
    -0.07
    kdir
    -0.07
     dram
    -0.07
    Ìģ
    -0.06
    RenderingContext
    -0.06
     republic
    -0.06
    POSITIVE LOGITS
    REA
    0.07
     Damian
    0.07
    /slick
    0.07
     gấp
    0.07
    105
    0.06
    Å©
    0.06
    redd
    0.06
     redd
    0.06
    à¸ģำหà¸Ļà¸Ķ
    0.06
    @nate
    0.06
    Activations Density 0.000%

    No Known Activations