© 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. 74875
    Prev
    Next
    INDEX
    Explanations

    segments related to technology and innovation in various sectors

    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
    duino
    -0.07
    canf
    -0.07
    searchModel
    -0.07
    odal
    -0.07
     sideline
    -0.07
    uyết
    -0.07
    lasses
    -0.07
    oose
    -0.07
    adders
    -0.07
    λί
    -0.07
    POSITIVE LOGITS
     solution
    0.07
     Solution
    0.07
     chosen
    0.07
    Case
    0.07
     case
    0.07
     challenge
    0.07
     saved
    0.07
     quote
    0.06
     Case
    0.06
    Describe
    0.06
    Activations Density 0.033%

    No Known Activations