© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 71099
    Prev
    Next
    INDEX
    Explanations

    references to currency manipulation by countries

    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
    latable
    -0.06
    apus
    -0.06
    lied
    -0.06
    çĵľ
    -0.06
    idata
    -0.06
    sett
    -0.06
    OTAL
    -0.06
    åĵģ
    -0.06
    rish
    -0.06
    ACHI
    -0.06
    POSITIVE LOGITS
     Traff
    0.06
    ENTRY
    0.06
     Report
    0.06
    eval
    0.06
     eval
    0.06
     report
    0.06
    uer
    0.06
    ington
    0.06
     human
    0.06
     Foreign
    0.06
    Activations Density 0.029%

    No Known Activations