© 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. 40995
    Prev
    Next
    INDEX
    Explanations

    collaborative learning activities

    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
    ëŀĻ
    -0.07
     actionTypes
    -0.07
    BOVE
    -0.07
    idon
    -0.07
    .React
    -0.07
     Bris
    -0.07
     εκεί
    -0.07
    åħ³
    -0.07
    inery
    -0.07
    acked
    -0.07
    POSITIVE LOGITS
     sharing
    0.06
     fert
    0.06
    eor
    0.06
     peer
    0.05
    wap
    0.05
     done
    0.05
     deadline
    0.05
     report
    0.05
    aise
    0.05
     Semester
    0.05
    Activations Density 0.004%

    No Known Activations