© 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. 15-LLAMASCOPE-RES-131K
    6. 26667
    Prev
    Next
    INDEX
    Explanations

    instances of the word "weise" and its variations, indicating a focus on the manner or way something is done

    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
    aida
    -0.07
    ick
    -0.07
     Yang
    -0.06
     dirt
    -0.05
     sun
    -0.05
     lic
    -0.05
     Sun
    -0.05
    ldr
    -0.05
     allies
    -0.05
     Outline
    -0.05
    POSITIVE LOGITS
    izon
    0.07
    stringLiteral
    0.07
    ioni
    0.07
    _READY
    0.07
    tings
    0.07
     defaultManager
    0.07
    esity
    0.06
    adge
    0.06
    /sources
    0.06
    cept
    0.06
    Activations Density 0.012%

    No Known Activations