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. 95964
    Prev
    Next
    INDEX
    Explanations

    references to military structures and historical context related to warfare

    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
    «ĺ
    -0.07
    nar
    -0.07
    orex
    -0.06
    orno
    -0.06
    جÙĪ
    -0.06
    ichten
    -0.06
    (Parcel
    -0.06
    shi
    -0.06
    rieving
    -0.06
    EventType
    -0.06
    POSITIVE LOGITS
    ooter
    0.07
    roscope
    0.06
    oman
    0.06
    .Utilities
    0.06
    oin
    0.06
    BOSE
    0.06
    esub
    0.06
    redit
    0.06
    alion
    0.06
    issy
    0.06
    Activations Density 0.709%

    No Known Activations