© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 15-LLAMASCOPE-RES-131K
    11. 88132
    Prev
    Next
    INDEX
    Explanations

    terms related to duality or comparative relationships

    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
    linger
    -0.07
    owler
    -0.07
    chio
    -0.07
    ersed
    -0.06
    olik
    -0.06
    ehler
    -0.06
    ering
    -0.06
    .asc
    -0.06
    eneric
    -0.06
    anter
    -0.06
    POSITIVE LOGITS
     parties
    0.10
     sides
    0.09
     Parties
    0.09
     ÑģÑĤоÑĢонÑĭ
    0.08
     side
    0.07
    archy
    0.07
     طرÙģ
    0.07
     taraf
    0.06
     camps
    0.06
     party
    0.06
    Activations Density 0.012%

    No Known Activations