© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 94606
    Prev
    Next
    INDEX
    Explanations

    technical terms related to mathematical functions and models

    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
    LBL
    -0.06
     Woodward
    -0.06
     budget
    -0.06
    pper
    -0.06
    -
    -0.06
     баг
    -0.05
    abus
    -0.05
     Lak
    -0.05
    .v
    -0.05
     —
    -0.05
    POSITIVE LOGITS
    cü
    0.08
     addCriterion
    0.07
    AZY
    0.07
    -transitional
    0.07
    ----------------------------------------------------------------------↵
    0.07
    å£
    0.07
    oyer
    0.07
    DEX
    0.07
     Temper
    0.07
    styleType
    0.07
    Activations Density 0.036%

    No Known Activations