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

    Neuronpedia

    Jacobian LensNEW
    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. 119263
    Prev
    Next
    INDEX
    Explanations

    phrases that convey stability and reliability in various contexts

    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
    TRACE
    -0.07
    kir
    -0.07
    appiness
    -0.07
    oods
    -0.07
    ellig
    -0.07
     assh
    -0.06
    ulk
    -0.06
    utan
    -0.06
    amel
    -0.06
    UBE
    -0.06
    POSITIVE LOGITS
    ly
    0.09
     základ
    0.08
     foundations
    0.07
    \grid
    0.07
     underlying
    0.07
    iscard
    0.07
     foundation
    0.07
    æĵļ
    0.07
    ierung
    0.07
     steady
    0.07
    Activations Density 0.010%

    No Known Activations