© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 77904
    Prev
    Next
    INDEX
    Explanations

    references to reading, literature, and written works

    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
    upp
    -0.07
     heard
    -0.07
     Heard
    -0.06
    Reusable
    -0.06
    Reuse
    -0.06
     reusable
    -0.06
    arty
    -0.06
    artment
    -0.06
     vide
    -0.05
    Ø´ÛĮ
    -0.05
    POSITIVE LOGITS
     aloud
    0.10
    outs
    0.08
    /watch
    0.07
    IED
    0.07
    AsStringAsync
    0.07
    bounce
    0.07
    uta
    0.07
    BuilderInterface
    0.06
     carefully
    0.06
     vor
    0.06
    Activations Density 0.080%

    No Known Activations