© 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. 17-LLAMASCOPE-RES-131K
    11. 59898
    Prev
    Next
    INDEX
    Explanations

    instructions or prompts to take action, particularly related to clicking or selecting links

    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
    dn
    -0.07
     festival
    -0.06
    yc
    -0.06
     festivals
    -0.06
     Fest
    -0.06
    hos
    -0.06
    ena
    -0.06
    ë
    -0.06
     Festival
    -0.06
    phia
    -0.05
    POSITIVE LOGITS
    pone
    0.07
    áze
    0.07
     BORDER
    0.07
    AREN
    0.07
    ">//
    0.07
     Denn
    0.07
    anford
    0.07
    bersome
    0.06
    åľ°ä¸ĭ
    0.06
     mz
    0.06
    Activations Density 0.005%

    No Known Activations