© 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. 77939
    Prev
    Next
    INDEX
    Explanations

    references to "this" in various contexts

    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
    hir
    -0.07
    iland
    -0.07
    rette
    -0.07
    lue
    -0.07
    bes
    -0.07
    vio
    -0.06
    conc
    -0.06
    ãģĿãĤĮãģ¯
    -0.06
    dom
    -0.06
    olate
    -0.06
    POSITIVE LOGITS
    iglia
    0.07
     because
    0.07
    emer
    0.06
     WaitForSeconds
    0.06
     Lump
    0.06
     PARTICULAR
    0.06
     myself
    0.06
     spur
    0.06
     particular
    0.06
    ön
    0.06
    Activations Density 0.020%

    No Known Activations