© 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. 77670
    Prev
    Next
    INDEX
    Explanations

    themes related to historical conflicts and their consequences

    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
    èĬĿ
    -0.07
    mans
    -0.06
    å¤ĩ
    -0.06
    ÑĤеÑħ
    -0.06
    ebin
    -0.06
    heid
    -0.06
    opup
    -0.06
    cling
    -0.06
    оди
    -0.06
    eron
    -0.06
    POSITIVE LOGITS
     evapor
    0.08
    odel
    0.07
     unfortunately
    0.07
    ereal
    0.07
     false
    0.07
    Unfortunately
    0.07
     Unfortunately
    0.07
    enance
    0.07
     fal
    0.07
     Garr
    0.06
    Activations Density 0.046%

    No Known Activations