© 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. 94570
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to Boolean algebra and arithmetic operations

    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
    .metro
    -0.07
    abstract
    -0.07
    amen
    -0.07
     Bry
    -0.06
    aku
    -0.06
    amer
    -0.06
    antry
    -0.06
    lications
    -0.06
    lek
    -0.06
    396
    -0.06
    POSITIVE LOGITS
     between
    0.10
    Between
    0.09
     Between
    0.09
    between
    0.08
    _between
    0.08
     giữa
    0.08
     BETWEEN
    0.08
    è¿IJ
    0.08
    /div
    0.08
     tussen
    0.07
    Activations Density 0.058%

    No Known Activations