© 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. 129965
    Prev
    Next
    INDEX
    Explanations

    instances of the word "what" 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
    ÙĤد
    -0.07
    боÑĤ
    -0.07
    wor
    -0.07
    ãģIJ
    -0.07
    quet
    -0.06
    çħ§
    -0.06
    nowledge
    -0.06
    ầm
    -0.06
    ivec
    -0.06
    ãģĿãĤĵãģª
    -0.06
    POSITIVE LOGITS
     happened
    0.07
     we
    0.07
     happening
    0.06
     happens
    0.06
    ppe
    0.06
    tributes
    0.06
    ched
    0.06
     ultimately
    0.06
     happen
    0.06
    ozem
    0.06
    Activations Density 0.011%

    No Known Activations