© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 74682
    Prev
    Next
    INDEX
    Explanations

    references to Bloomberg in contexts related to finance and industry analysis

    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
    inen
    -0.07
    ziej
    -0.07
    Ìī
    -0.07
    uran
    -0.07
    eler
    -0.06
    OE
    -0.06
    AdapterManager
    -0.06
    aload
    -0.06
    ses
    -0.06
    nbsp
    -0.06
    POSITIVE LOGITS
    .com
    0.08
    entine
    0.07
    usercontent
    0.07
    zano
    0.07
    ued
    0.07
     Lup
    0.07
    .AttributeSet
    0.06
    arti
    0.06
    UNT
    0.06
    enda
    0.06
    Activations Density 0.001%

    No Known Activations