© 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. 118247
    Prev
    Next
    INDEX
    Explanations

    code structure and flow control elements

    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
    alach
    -0.07
    عÙĦÙĪÙħات
    -0.06
    omon
    -0.06
    stackpath
    -0.06
     collaps
    -0.06
    oste
    -0.06
    ód
    -0.06
     SPDX
    -0.06
     جÙĦ
    -0.06
    alaxy
    -0.06
    POSITIVE LOGITS
    .ly
    0.07
     addCriterion
    0.07
    sak
    0.07
    ãĥ³ãĤº
    0.07
    RuleContext
    0.07
    ests
    0.07
    ward
    0.06
     case
    0.06
    ย
    0.06
    angers
    0.06
    Activations Density 0.001%

    No Known Activations