© 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. 15-LLAMASCOPE-RES-131K
    11. 27568
    Prev
    Next
    INDEX
    Explanations

    references to market dynamics and their effects on society

    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
     chop
    -0.06
    687
    -0.06
    iku
    -0.06
    htub
    -0.06
    ailability
    -0.05
    IGIN
    -0.05
    zend
    -0.05
     Sur
    -0.05
     Boo
    -0.05
    iken
    -0.05
    POSITIVE LOGITS
    andest
    0.08
    idal
    0.07
    ifestyles
    0.07
    usra
    0.06
    isos
    0.06
    reck
    0.06
    ụ
    0.06
    ocrates
    0.06
    idders
    0.06
    058
    0.06
    Activations Density 0.053%

    No Known Activations