© 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. 87995
    Prev
    Next
    INDEX
    Explanations

    key terms related to changes and stability within systems

    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
    elo
    -0.06
    anon
    -0.06
    anos
    -0.06
    axter
    -0.05
     Reco
    -0.05
    емо
    -0.05
     nonzero
    -0.05
    ilot
    -0.05
     Blvd
    -0.05
    ipur
    -0.05
    POSITIVE LOGITS
     unchanged
    0.28
     remained
    0.17
     remain
    0.17
     remains
    0.16
     intact
    0.15
    remain
    0.15
     retains
    0.15
     zůst
    0.15
    unch
    0.14
     retain
    0.14
    Activations Density 0.222%

    No Known Activations