© 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. 75340
    Prev
    Next
    INDEX
    Explanations

    references to materials and processes involved in welding and adhesive application

    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
    isko
    -0.07
    otten
    -0.07
    iti
    -0.07
    ovit
    -0.06
    -heart
    -0.06
    449
    -0.06
    æĬij
    -0.06
    yme
    -0.06
     göl
    -0.06
     Setter
    -0.06
    POSITIVE LOGITS
     surfaces
    0.09
     surface
    0.08
    surface
    0.07
     walls
    0.07
    por
    0.07
     substr
    0.06
    substr
    0.06
    uctions
    0.06
    ì¹Ļ
    0.06
     Surface
    0.06
    Activations Density 0.011%

    No Known Activations