© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 62532
    Prev
    Next
    INDEX
    Explanations

    references to educational participation and transitions

    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
    ring
    -0.06
    phia
    -0.06
    resco
    -0.06
    onn
    -0.06
    ingo
    -0.06
    ima
    -0.06
    enes
    -0.06
    ux
    -0.06
    tern
    -0.06
    cesso
    -0.05
    POSITIVE LOGITS
     themselves
    0.08
     ÙĩÛĮ
    0.07
    Ư
    0.07
    FromBody
    0.07
    orno
    0.07
    GLOSS
    0.07
    Reviewer
    0.07
    ç´¹
    0.07
    stagram
    0.07
    ayar
    0.07
    Activations Density 0.016%

    No Known Activations