© 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. 75216
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and activities involving data manipulation

    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
    addir
    -0.08
     mkdir
    -0.07
    mkdir
    -0.07
    	mkdir
    -0.07
    awning
    -0.07
    еÑĩ
    -0.06
     glGen
    -0.06
    avax
    -0.06
    ulace
    -0.06
     shredd
    -0.06
    POSITIVE LOGITS
     update
    0.14
    update
    0.14
    æĽ´æĸ°
    0.14
     updating
    0.14
     Update
    0.13
     updates
    0.13
     Updating
    0.13
     Updates
    0.13
     æĽ´æĸ°
    0.13
    _update
    0.13
    Activations Density 0.129%

    No Known Activations