© 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. 55853
    Prev
    Next
    INDEX
    Explanations

    mentions of public-private partnerships and their impact on service provision

    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
    oltip
    -0.07
    -nil
    -0.06
    ãĥ¬ãĤ¤
    -0.06
     laying
    -0.06
     cul
    -0.06
     ÙĩÙĪ
    -0.06
     Cruc
    -0.06
     Necessary
    -0.06
    psc
    -0.06
     æ´»
    -0.06
    POSITIVE LOGITS
     vending
    0.09
     vend
    0.08
    omat
    0.08
     disp
    0.08
     dispens
    0.07
     machines
    0.07
    iday
    0.07
    Ĥ¤
    0.07
    serve
    0.07
     Vend
    0.07
    Activations Density 0.005%

    No Known Activations