© 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. 126122
    Prev
    Next
    INDEX
    Explanations

    references to locations, events, and community gatherings

    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
    _ASSUME
    -0.08
    olta
    -0.07
    .tool
    -0.07
    tiv
    -0.07
    CRET
    -0.07
    Appear
    -0.07
     Garten
    -0.07
     гла
    -0.07
    cai
    -0.07
    crawl
    -0.07
    POSITIVE LOGITS
    ardu
    0.08
     Memorial
    0.06
    ouro
    0.06
    ahr
    0.06
     downtown
    0.06
     Park
    0.06
     World
    0.06
     Interstate
    0.06
     Proposal
    0.06
     Hlav
    0.06
    Activations Density 0.056%

    No Known Activations