© 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. 89396
    Prev
    Next
    INDEX
    Explanations

    phrases related to measurement and quantification

    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
    vrd
    -0.07
    .bd
    -0.07
    plib
    -0.06
     Affero
    -0.06
    еÑĢжав
    -0.06
     addCriterion
    -0.06
    asti
    -0.06
    _codegen
    -0.06
    blr
    -0.06
    .lu
    -0.06
    POSITIVE LOGITS
    æİī
    0.07
    zt
    0.06
    ik
    0.06
    ë¦Ħ
    0.06
    rop
    0.06
    اغ
    0.06
    raph
    0.06
    ac
    0.06
    acco
    0.06
    iken
    0.06
    Activations Density 0.012%

    No Known Activations