© 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. 87850
    Prev
    Next
    INDEX
    Explanations

    financial terms related to market dynamics and deals

    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
     ICO
    -0.08
     createAction
    -0.08
     ActionTypes
    -0.07
    izm
    -0.07
    458
    -0.07
    aland
    -0.07
    aday
    -0.07
    hud
    -0.06
    ož
    -0.06
    upil
    -0.06
    POSITIVE LOGITS
     Cop
    0.08
    avin
    0.07
    ollen
    0.07
     alternative
    0.07
    ibble
    0.07
    anos
    0.06
    Independ
    0.06
     cust
    0.06
    agn
    0.06
     alternate
    0.06
    Activations Density 0.001%

    No Known Activations