© 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. 17-LLAMASCOPE-RES-131K
    11. 70695
    Prev
    Next
    INDEX
    Explanations

    instances of the word "as" used in various contexts

    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
    ÑĮв
    -0.07
    ysz
    -0.07
    ãĤŀ
    -0.07
    abyrin
    -0.07
    eÄį
    -0.07
    _dispatch
    -0.07
    erland
    -0.07
    .mods
    -0.07
     TÆ°
    -0.06
    uchs
    -0.06
    POSITIVE LOGITS
     part
    0.06
    ner
    0.06
    ryn
    0.06
    _va
    0.06
    omic
    0.06
    .SC
    0.06
     ut
    0.05
     interest
    0.05
    pletion
    0.05
     analog
    0.05
    Activations Density 0.026%

    No Known Activations