© 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. 61524
    Prev
    Next
    INDEX
    Explanations

    negative qualifiers and references to limitations or challenges

    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
    ÑĪÑĥ
    -0.07
     isolated
    -0.06
     AUTHORS
    -0.06
    å¯
    -0.06
    sez
    -0.06
    /component
    -0.06
    isten
    -0.06
     poil
    -0.06
    vil
    -0.06
    ãģķãģ¾
    -0.06
    POSITIVE LOGITS
     necessarily
    0.08
    ecessarily
    0.07
    etas
    0.07
    ibt
    0.07
     part
    0.07
    ERM
    0.06
     nor
    0.06
    anke
    0.06
    ãĥĥãĥĹ
    0.06
    imulator
    0.06
    Activations Density 0.025%

    No Known Activations