© 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. 84586
    Prev
    Next
    INDEX
    Explanations

    phrases related to business development and startups

    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
    oria
    -0.07
    ORIA
    -0.07
     درÛĮ
    -0.07
    辺
    -0.07
    OAD
    -0.07
    edom
    -0.06
    âĢĮاÙĨ
    -0.06
    еÑĢеÑĩ
    -0.06
     wid
    -0.06
    chio
    -0.06
    POSITIVE LOGITS
     establish
    0.09
     establishment
    0.08
    819
    0.08
    new
    0.08
     new
    0.08
    establish
    0.08
     establishing
    0.08
     brand
    0.08
    æĸ°çļĦ
    0.08
    .initial
    0.07
    Activations Density 0.026%

    No Known Activations