© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 39549
    Prev
    Next
    INDEX
    Explanations

    keywords and terminology related to digital rights and legal agreements

    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
    ÐĶÐļ
    -0.08
    elmet
    -0.07
    rsp
    -0.07
    ÑĢап
    -0.07
    DataType
    -0.07
    conomy
    -0.07
    ãģªãģĬ
    -0.07
    }}},↵
    -0.06
    天天
    -0.06
    Ñģ
    -0.06
    POSITIVE LOGITS
     how
    0.12
     why
    0.09
     learn
    0.09
     a
    0.08
    how
    0.08
     an
    0.08
     explains
    0.07
     Learn
    0.07
     "
    0.07
     describes
    0.07
    Activations Density 0.018%

    No Known Activations