© 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. 62323
    Prev
    Next
    INDEX
    Explanations

    phrases related to one-time events or costs

    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
     latter
    -0.07
    isse
    -0.06
    Ñģол
    -0.06
    инг
    -0.06
    idel
    -0.06
    ese
    -0.06
    ữ
    -0.06
     Apost
    -0.06
    764
    -0.06
    /orders
    -0.06
    POSITIVE LOGITS
    /single
    0.09
    orarily
    0.07
    unda
    0.07
    tons
    0.07
    echan
    0.06
    utive
    0.06
    æĢ§
    0.06
    -use
    0.06
    coder
    0.06
    \TestCase
    0.06
    Activations Density 0.005%

    No Known Activations