© 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. 88383
    Prev
    Next
    INDEX
    Explanations

    expressions of collective experience and emotion

    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
    ToWorld
    -0.09
    è¼Ķ
    -0.08
    .Cursors
    -0.07
     Incontri
    -0.07
    foy
    -0.07
    obao
    -0.07
    oplan
    -0.07
    uddy
    -0.07
     addCriterion
    -0.07
    olang
    -0.07
    POSITIVE LOGITS
     etc
    0.06
     yes
    0.05
    ICE
    0.05
    eline
    0.05
     pumping
    0.05
    kaar
    0.05
    uchs
    0.05
     Connection
    0.05
     yeah
    0.05
    AYER
    0.05
    Activations Density 0.003%

    No Known Activations