© 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. 125219
    Prev
    Next
    INDEX
    Explanations

    phrases related to conflict and its associated dynamics

    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
    ÑĢей
    -0.07
    aves
    -0.07
     sebuah
    -0.07
     ÙĦÙĥÙĦ
    -0.06
    CRE
    -0.06
     stanov
    -0.06
    .tbl
    -0.06
    obi
    -0.06
    ãĥªãĥ³ãĤ°
    -0.06
    ilon
    -0.06
    POSITIVE LOGITS
     themselves
    0.21
     their
    0.14
    their
    0.12
    Their
    0.10
     other
    0.10
     others
    0.10
     leurs
    0.09
    others
    0.09
     Their
    0.09
     THEIR
    0.09
    Activations Density 0.058%

    No Known Activations