© 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. 17-LLAMASCOPE-RES-131K
    11. 89132
    Prev
    Next
    INDEX
    Explanations

    references to concepts related to "multi" or "multilateral."

    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
    esis
    -0.07
    ald
    -0.07
    ramids
    -0.07
    ÃĻ
    -0.06
    eselect
    -0.06
    Ze
    -0.06
    ãĤ·ãĥ§ãĥ³
    -0.06
    аннÑĸ
    -0.06
    389
    -0.06
    keeping
    -0.06
    POSITIVE LOGITS
    multi
    0.08
     multi
    0.07
     sclerosis
    0.07
    acz
    0.07
    asics
    0.07
    -multi
    0.07
    UFFIX
    0.06
    oya
    0.06
     coloured
    0.06
    tier
    0.06
    Activations Density 0.015%

    No Known Activations