© 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. 89021
    Prev
    Next
    INDEX
    Explanations

    complex relationships and evaluations of situations or concepts

    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
    rary
    -0.07
    WithTag
    -0.06
    ogenous
    -0.06
    olet
    -0.06
    trace
    -0.06
    emento
    -0.06
    egt
    -0.06
     ()->
    -0.06
    lep
    -0.06
    anje
    -0.06
    POSITIVE LOGITS
     although
    0.13
     aunque
    0.12
     though
    0.12
    though
    0.11
     ÑħоÑĤÑı
    0.11
    although
    0.11
    èĻ½çĦ¶
    0.10
     mặc
    0.10
    èĻ½
    0.09
     Though
    0.09
    Activations Density 0.071%

    No Known Activations