© 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. 57078
    Prev
    Next
    INDEX
    Explanations

    references to 360-degree viewpoints or experiences

    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
    avec
    -0.08
    ãĥªãĥ¼ãĤº
    -0.07
    acy
    -0.07
    λη
    -0.07
    IMA
    -0.07
    ossal
    -0.07
    лоп
    -0.07
    ocker
    -0.07
    MOTE
    -0.07
    Interfaces
    -0.07
    POSITIVE LOGITS
    s
    0.09
    imensional
    0.07
    -degree
    0.07
    sus
    0.07
    ties
    0.06
     view
    0.06
    0.06
     fashion
    0.06
     degree
    0.06
    ãĥ¼ãĥŃ
    0.06
    Activations Density 0.003%

    No Known Activations