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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 126478
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to geometry and data representation

    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
    iks
    -0.07
     Lambert
    -0.07
     Cush
    -0.06
    ADED
    -0.06
     Decimal
    -0.06
    ̣
    -0.06
     Hick
    -0.06
    vtk
    -0.06
    ढ
    -0.06
    abant
    -0.06
    POSITIVE LOGITS
    isoner
    0.07
    ัà¸Ļà¹Ħà¸Ķ
    0.06
    اÛĮز
    0.06
    uis
    0.06
    CCCCCC
    0.06
    sonian
    0.06
    æī£
    0.06
     मण
    0.06
    .communication
    0.06
    ricks
    0.06
    Activations Density 0.063%

    No Known Activations