© 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. 5-LLAMASCOPE-RES-131K
    11. 125525
    Prev
    Next
    INDEX
    Explanations

    terms related to 360-degree perspectives and views

    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
    dad
    -0.07
    جÛĮ
    -0.07
    607
    -0.07
    /testing
    -0.07
    Ptr
    -0.06
    éra
    -0.06
    ieber
    -0.06
    ģm
    -0.06
     âĨIJ
    -0.06
    ENDOR
    -0.06
    POSITIVE LOGITS
    hart
    0.06
    aware
    0.06
    Configurer
    0.06
    artin
    0.06
    .camel
    0.06
    agram
    0.06
    typeorm
    0.06
    εÏĤ
    0.06
    geh
    0.06
     spectrum
    0.06
    Activations Density 0.003%

    No Known Activations