© 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. 15-LLAMASCOPE-RES-131K
    11. 103178
    Prev
    Next
    INDEX
    Explanations

    concepts related to collaboration and value creation in business

    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
    ypi
    -0.08
    abant
    -0.07
    occo
    -0.07
    dbcTemplate
    -0.07
     @_
    -0.07
    dál
    -0.06
    gba
    -0.06
    YPE
    -0.06
    gregator
    -0.06
    emain
    -0.06
    POSITIVE LOGITS
     mutual
    0.09
    -shared
    0.08
     gemeins
    0.08
    shared
    0.08
    .shared
    0.08
    Shared
    0.07
     sharing
    0.07
     shared
    0.07
     pooling
    0.07
     pooled
    0.07
    Activations Density 0.030%

    No Known Activations