© 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. 15-LLAMASCOPE-RES-131K
    11. 89348
    Prev
    Next
    INDEX
    Explanations

    terms related to disturbances or alterations in conditions

    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
    erosis
    -0.09
    à¸Ķà¸Ļ
    -0.08
    вано
    -0.08
    омеÑĢ
    -0.08
    imals
    -0.08
    erset
    -0.07
    avors
    -0.07
    ued
    -0.07
    ery
    -0.07
    osen
    -0.07
    POSITIVE LOGITS
    elm
    0.08
    amel
    0.07
    folio
    0.07
    167
    0.07
    weet
    0.07
    utor
    0.07
    ault
    0.07
    odox
    0.07
    169
    0.07
    urbed
    0.06
    Activations Density 0.006%

    No Known Activations