© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 60429
    Prev
    Next
    INDEX
    Explanations

    references to combat capabilities and personal strength

    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
    оÑĤоÑĢ
    -0.07
    affected
    -0.07
    λοÏį
    -0.07
    icos
    -0.07
    849
    -0.06
    åģ·
    -0.06
    _syntax
    -0.06
    Affected
    -0.06
    sse
    -0.06
    lage
    -0.06
    POSITIVE LOGITS
     formidable
    0.09
     powerful
    0.08
     threat
    0.07
     intimid
    0.07
     intimidating
    0.07
     effective
    0.07
     intimidation
    0.07
     dangerous
    0.07
     capabilities
    0.07
     capability
    0.07
    Activations Density 0.051%

    No Known Activations