© 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. 22-LLAMASCOPE-RES-131K
    11. 4074
    Prev
    Next
    INDEX
    Explanations

    phrases indicating an introduction or emphasis on a subject

    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
    idi
    -0.07
    IDI
    -0.07
    pf
    -0.07
    holm
    -0.06
    ovy
    -0.06
    og
    -0.06
    vious
    -0.06
    nob
    -0.06
    dej
    -0.06
    aby
    -0.06
    POSITIVE LOGITS
     because
    0.10
     partly
    0.09
     is
    0.09
    ï¼ĮåĽłä¸º
    0.09
     owed
    0.08
     porque
    0.08
     fact
    0.08
     reflect
    0.08
    åİŁåĽł
    0.08
     owes
    0.08
    Activations Density 0.031%

    No Known Activations