© 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. 15-LLAMASCOPE-RES-131K
    11. 89880
    Prev
    Next
    INDEX
    Explanations

    instances of the word "two" and its related forms, indicating duality or multiplicity

    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
     directly
    -0.06
     Coff
    -0.06
    ugin
    -0.06
    ring
    -0.06
    FindBy
    -0.06
    gy
    -0.06
    onec
    -0.05
    群
    -0.05
    ray
    -0.05
    ibrated
    -0.05
    POSITIVE LOGITS
     equally
    0.08
    ippo
    0.08
     distinct
    0.07
    åIJĮæĻĤ
    0.07
    Å¡t
    0.07
    oppers
    0.07
     simultaneous
    0.07
    akers
    0.07
    847
    0.07
    viders
    0.06
    Activations Density 0.020%

    No Known Activations