Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 125731
    Prev
    Next
    INDEX
    Explanations

    comment blocks and structured annotations in code

    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
    uger
    -0.07
    uels
    -0.07
    rijk
    -0.07
    ogl
    -0.06
    Terminal
    -0.06
     terminal
    -0.06
    arda
    -0.06
    alara
    -0.06
    258
    -0.06
    xd
    -0.06
    POSITIVE LOGITS
    Ymd
    0.07
    vertime
    0.07
    IDL
    0.07
    	class
    0.06
    olvers
    0.06
    LARI
    0.06
    alaxy
    0.06
    INGER
    0.06
     ÑĢÑĥкÑĥ
    0.06
    spiracy
    0.06
    Activations Density 0.004%

    No Known Activations