© 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. 129110
    Prev
    Next
    INDEX
    Explanations

    references to creativity and creative professionals in the media industry

    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
    iez
    -0.07
    wine
    -0.07
    acher
    -0.07
    akedown
    -0.07
    stadt
    -0.06
    едак
    -0.06
     Cycl
    -0.06
    argon
    -0.06
    ocks
    -0.06
     ÑģлÑĥ
    -0.06
    POSITIVE LOGITS
     agency
    0.09
     ad
    0.09
     agencies
    0.09
    Agency
    0.09
     creat
    0.09
     Agencies
    0.09
    VML
    0.09
     Agency
    0.08
    agency
    0.07
    oola
    0.07
    Activations Density 0.046%

    No Known Activations