© 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. 59979
    Prev
    Next
    INDEX
    Explanations

    phrases related to events, locations, and social interactions

    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
    èĨ
    -0.06
    odd
    -0.06
    oki
    -0.06
    áÅĻi
    -0.06
     seldom
    -0.06
    WD
    -0.06
    θι
    -0.06
    .parser
    -0.06
    éis
    -0.06
    ãĥ¼ãĥĨãĤ£
    -0.06
    POSITIVE LOGITS
     kdyby
    0.11
     would
    0.09
    would
    0.08
     given
    0.08
     Would
    0.08
     if
    0.08
     or
    0.08
     hätte
    0.07
    Would
    0.07
     Easily
    0.07
    Activations Density 0.024%

    No Known Activations