© 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. 84987
    Prev
    Next
    INDEX
    Explanations

    instances of the word "it" and variations thereof

    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
     str
    -0.06
     Cav
    -0.06
    ENT
    -0.06
     Conf
    -0.05
     ty
    -0.05
    _ed
    -0.05
     stuff
    -0.05
     jack
    -0.05
    .ec
    -0.05
     internal
    -0.05
    POSITIVE LOGITS
    BoxLayout
    0.08
    adio
    0.07
     bois
    0.07
    elen
    0.07
    /options
    0.07
    ç´ļ
    0.07
    /session
    0.07
    alama
    0.07
    adol
    0.06
    inning
    0.06
    Activations Density 0.019%

    No Known Activations