© 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. 74594
    Prev
    Next
    INDEX
    Explanations

    references to the concept of significance or meaning

    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
     reason
    -0.08
    aura
    -0.08
    rett
    -0.07
    .toolbox
    -0.07
    ستاÙĨ
    -0.07
    llib
    -0.07
    ķĮ
    -0.07
    ãģĵãģĿ
    -0.07
    itals
    -0.07
    arlo
    -0.07
    POSITIVE LOGITS
     something
    0.08
     exactly
    0.08
     nothing
    0.07
    'gc
    0.07
    ionario
    0.06
    nothing
    0.06
    ÑĪкÑĥ
    0.06
    endir
    0.06
     Trouble
    0.06
     Exactly
    0.06
    Activations Density 0.014%

    No Known Activations