© 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. 17277
    Prev
    Next
    INDEX
    Explanations

    phrases indicating statistical significance or lack thereof in research results

    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
     Ridley
    -0.08
    -IS
    -0.06
    uetype
    -0.06
     parl
    -0.06
    çĭIJ
    -0.06
    жа
    -0.06
    ettle
    -0.06
     mog
    -0.06
    iat
    -0.06
    ITUDE
    -0.06
    POSITIVE LOGITS
     difference
    0.10
    difference
    0.09
     differences
    0.09
     Difference
    0.09
     nor
    0.08
     any
    0.08
    ifference
    0.08
     significant
    0.07
     diferencia
    0.07
    Difference
    0.07
    Activations Density 0.024%

    No Known Activations