Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 95597
    Prev
    Next
    INDEX
    Explanations

    references to diplomatic negotiations and mediation efforts

    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
    ALTH
    -0.07
    ãģ¡ãģ¯
    -0.07
    mith
    -0.07
    alo
    -0.07
    las
    -0.06
    BOSE
    -0.06
    udget
    -0.06
    npos
    -0.06
    ystone
    -0.06
    MainFrame
    -0.06
    POSITIVE LOGITS
    ory
    0.07
    .tc
    0.06
    eff
    0.06
     Pair
    0.05
     Curt
    0.05
    anked
    0.05
    inati
    0.05
    ennes
    0.05
     States
    0.05
     Lun
    0.05
    Activations Density 0.014%

    No Known Activations